© 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. 4136
    Prev
    Next
    INDEX
    Explanations

    words related to flexibility and adaptability

    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
    195
    +0.15
    0.7%
    718
    +0.15
    0.7%
    68
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.27
    326
    +0.15
    0.23
    464
    +0.13
    0.11
    Negative Logits
     Gon
    -0.68
    upt
    -0.68
    hood
    -0.64
    ansom
    -0.64
    oping
    -0.63
    Magikarp
    -0.62
     Ragnarok
    -0.62
     Ferdinand
    -0.62
    otle
    -0.61
    OCK
    -0.61
    POSITIVE LOGITS
    ibilities
    0.92
    iture
    0.90
    ibly
    0.88
    enhagen
    0.87
    olyn
    0.83
    ibility
    0.82
    elines
    0.80
    ilitation
    0.78
    olini
    0.78
    elin
    0.77
    Activations Density 7.694%

    No Known Activations