© 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. 12747
    Prev
    Next
    INDEX
    Explanations

    structured pricing information for a subscription service

    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
    565
    +0.08
    0.5%
    460
    +0.08
    0.4%
    259
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    211
    +0.08
    0.01
    739
    +0.08
    0.01
    325
    +0.07
    0.01
    Negative Logits
    jon
    -0.68
    wcs
    -0.61
     Cheong
    -0.60
    ffe
    -0.59
    nik
    -0.58
    76561
    -0.57
     polyg
    -0.57
    jad
    -0.56
    jug
    -0.56
    ht
    -0.56
    POSITIVE LOGITS
    é¾įåĸļ士
    0.59
     Adjust
    0.59
     Dragonbound
    0.56
    leness
    0.55
    asks
    0.54
    bucks
    0.54
     Reborn
    0.54
     Deliver
    0.54
     Compensation
    0.54
    SIZE
    0.54
    Activations Density 0.058%

    No Known Activations