© 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. 240
    Prev
    Next
    INDEX
    Explanations

    references to public infrastructure and policy-related discussions, especially related to environmental and urban planning

    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
    476
    +0.09
    0.5%
    407
    +0.09
    0.5%
    679
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.09
    0.13
    195
    +0.09
    0.03
    566
    +0.09
    0.08
    Negative Logits
    ussia
    -0.66
     administr
    -0.58
    ammy
    -0.56
     ceremon
    -0.55
    iety
    -0.55
     moth
    -0.55
    anwhile
    -0.54
    fighting
    -0.54
    ricular
    -0.54
    uclear
    -0.53
    POSITIVE LOGITS
     attest
    0.77
    geries
    0.74
     Parables
    0.73
     Thrones
    0.72
    Ĭ±
    0.71
    £ı
    0.71
    suggest
    0.68
    antage
    0.64
     predicting
    0.62
    gery
    0.62
    Activations Density 2.529%

    No Known Activations