© 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. 33852
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical information and data

    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
    183
    +0.12
    0.6%
    554
    +0.11
    0.5%
    447
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.22
    99
    +0.11
    0.10
    288
    +0.10
    0.20
    Negative Logits
    ãĥ£
    -0.82
    ulative
    -0.73
    arnaev
    -0.72
    dule
    -0.69
    ptive
    -0.69
     dilig
    -0.66
    perature
    -0.64
    erate
    -0.61
     Pwr
    -0.60
    ENCY
    -0.59
    POSITIVE LOGITS
    obyl
    0.97
    alia
    0.88
    ication
    0.82
    ado
    0.82
    hedon
    0.81
    lihood
    0.79
    adoes
    0.79
    odon
    0.78
    acles
    0.78
    shire
    0.76
    Activations Density 7.754%

    No Known Activations