© 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. 7041
    Prev
    Next
    INDEX
    Explanations

    names of places or people

    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
    240
    +0.22
    0.7%
    119
    +0.18
    0.5%
    163
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    220
    +0.22
    0.06
    429
    +0.18
    0.05
    232
    +0.16
    0.06
    Negative Logits
    aution
    -1.45
    enhagen
    -1.34
     nomine
    -1.24
     confir
    -1.14
     mosqu
    -1.13
     indo
    -1.11
    ãĥ¯
    -1.10
     tremend
    -1.09
     derog
    -1.09
     Clicker
    -1.07
    POSITIVE LOGITS
    orses
    1.82
    awk
    1.82
    azard
    1.73
    undred
    1.72
    anging
    1.71
    ttp
    1.68
    wy
    1.65
    ulk
    1.65
    ackers
    1.64
    ollow
    1.64
    Activations Density 0.799%

    No Known Activations