© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 6484
    Prev
    Next
    INDEX
    Explanations

    keyword combinations that indicate news reporting about specific events, health issues, and community protests

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    393
    +0.26
    0.8%
    385
    +0.18
    0.6%
    649
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    385
    +0.26
    0.08
    608
    +0.18
    0.08
    614
    +0.14
    0.05
    Negative Logits
    ratulations
    -1.17
    merce
    -1.15
    estinal
    -1.07
    hai
    -1.06
    acci
    -1.05
    inguishable
    -1.05
    mun
    -1.04
    ashtra
    -1.03
     carbohyd
    -1.01
    iltration
    -1.01
    POSITIVE LOGITS
     afar
    1.63
     whence
    1.41
     inside
    1.23
     Above
    1.09
     abroad
    1.08
     Wow
    0.99
     underneath
    0.99
     elsewhere
    0.99
     within
    0.98
     outside
    0.96
    Activations Density 0.987%

    No Known Activations