© 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 Local
    5. 6-RES_SCL-AJT
    6. 4849
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to programming or computer science

    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
    266
    +0.02
    0.6%
    246
    +0.02
    0.5%
    14
    +0.02
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.02
    0.47
    393
    +0.02
    0.41
    64
    +0.02
    -0.33
    Negative Logits
     shipping
    -0.10
    ty
    -0.10
     service
    -0.09
     arrangements
    -0.09
     warr
    -0.09
    iants
    -0.09
     ship
    -0.09
     lighthouse
    -0.09
     ware
    -0.09
     Kelvin
    -0.08
    POSITIVE LOGITS
    berman
    0.14
    Mos
    0.13
    rican
    0.12
    ggle
    0.10
    ppo
    0.10
    jp
    0.10
    amaru
    0.10
    FN
    0.10
    Race
    0.10
    soDeliveryDate
    0.10
    Activations Density 19.611%

    No Known Activations