© 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. 40045
    Prev
    Next
    INDEX
    Explanations

    words related to social sciences, particularly sociology, and possibly internet-related terms like "cybernetics."

    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
    483
    +0.12
    0.5%
    447
    +0.11
    0.5%
    508
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.12
    -0.05
    675
    +0.11
    0.15
    154
    +0.10
    0.16
    Negative Logits
    ĸļ
    -0.86
     chunks
    -0.68
     socket
    -0.68
     Cheong
    -0.68
     contention
    -0.67
     Revel
    -0.66
     compression
    -0.64
     spoilers
    -0.64
     unmarked
    -0.64
     toast
    -0.64
    POSITIVE LOGITS
    alyst
    0.90
    ALLY
    0.90
    icians
    0.88
    ically
    0.84
    alysis
    0.81
    cient
    0.78
    ombat
    0.78
    vice
    0.77
    analy
    0.77
    ê
    0.77
    Activations Density 13.332%

    No Known Activations