© 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 Local
    9. 6-RES_SCL-AJT
    11. 31829
    Prev
    Next
    INDEX
    Explanations

    abbreviations or acronyms followed by a question and answer format

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.15
    0.8%
    634
    +0.11
    0.6%
    270
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.15
    0.66
    447
    +0.11
    0.68
    64
    +0.09
    -0.17
    Negative Logits
    fif
    -0.70
    taboola
    -0.70
     surpr
    -0.60
     Seym
    -0.59
    pard
    -0.59
    mine
    -0.59
    fish
    -0.58
    milo
    -0.58
    Pi
    -0.58
     Pengu
    -0.58
    POSITIVE LOGITS
     Armageddon
    0.61
     Dragonbound
    0.59
     Ready
    0.59
     ministry
    0.58
     consultancy
    0.57
    idated
    0.57
     guru
    0.57
     apparel
    0.56
    èĢħ
    0.56
     outlet
    0.55
    Activations Density 10.562%

    No Known Activations