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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 13148
    Prev
    Next
    INDEX
    Explanations

    names and references related to authors, scripts, and writing

    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
    554
    +0.14
    0.5%
    545
    +0.14
    0.5%
    16
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.13
    326
    +0.14
    0.11
    406
    +0.14
    0.08
    Negative Logits
    ĸļ
    -1.27
    efully
    -1.03
    ¬¼
    -0.89
    Ħ¢
    -0.89
    eting
    -0.86
    earance
    -0.83
    ingly
    -0.81
    elled
    -0.81
    esy
    -0.81
    ³
    -0.81
    POSITIVE LOGITS
    idad
    1.39
    itous
    1.21
    ity
    1.07
    oad
    1.06
    icio
    1.06
    ities
    1.05
    tarians
    1.05
     Castro
    1.03
    gence
    1.01
    mma
    1.00
    Activations Density 1.588%

    No Known Activations