© 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 EvalsExportsinterp-engineNEWAPI 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. 2374
    Prev
    Next
    INDEX
    Explanations

    historical references and mentions of past events

    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
    288
    +0.29
    0.9%
    290
    +0.17
    0.5%
    459
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    290
    +0.29
    0.04
    724
    +0.17
    0.05
    288
    +0.15
    0.05
    Negative Logits
    leased
    -1.21
    amina
    -1.15
    inki
    -1.14
    pose
    -1.11
    orc
    -1.11
    pload
    -1.11
    aton
    -1.10
    ishable
    -1.08
    alties
    -1.06
    ressed
    -1.06
    POSITIVE LOGITS
     buffs
    1.26
    making
    1.12
     Corpus
    1.09
    makers
    1.07
     history
    1.06
    orians
    1.04
    ISTORY
    1.02
     Echoes
    1.01
    geist
    1.00
     tale
    1.00
    Activations Density 0.633%

    No Known Activations