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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 32891
    Prev
    Next
    INDEX
    Explanations

    symbols and patterns, possibly related to technical or code-like content

    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
    201
    +0.11
    0.6%
    274
    +0.10
    0.6%
    651
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    402
    +0.11
    0.09
    276
    +0.10
    0.13
    728
    +0.10
    0.07
    Negative Logits
    ippi
    -0.60
    osaurus
    -0.57
    uania
    -0.57
    ouver
    -0.57
    alez
    -0.53
     Colo
    -0.52
    geist
    -0.51
    ikarp
    -0.51
    pas
    -0.50
     Dickinson
    -0.50
    POSITIVE LOGITS
    \\\\
    0.65
    cffffcc
    0.63
    Ly
    0.59
    -|
    0.58
    é¾įåĸļ士
    0.58
    vernment
    0.57
    cffff
    0.55
    standard
    0.54
    CLASSIFIED
    0.53
    URN
    0.52
    Activations Density 5.894%

    No Known Activations