© 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
    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. 4650
    Prev
    Next
    INDEX
    Explanations

    comparisons or opinions expressed in a critical or analytical manner

    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
    1.0%
    393
    +0.10
    0.7%
    566
    +0.09
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.15
    0.31
    160
    +0.10
    0.27
    255
    +0.09
    0.14
    Negative Logits
    Va
    -0.50
    cies
    -0.44
     Herrera
    -0.43
    atlantic
    -0.43
    oway
    -0.42
     thirds
    -0.42
     Ghana
    -0.40
     Polk
    -0.40
     Yel
    -0.40
     Panama
    -0.40
    POSITIVE LOGITS
    self
    0.71
    chy
    0.70
    unes
    0.68
    atically
    0.66
    iner
    0.65
    ueller
    0.61
    zik
    0.59
     beh
    0.56
    alian
    0.55
     raining
    0.54
    Activations Density 13.240%

    No Known Activations