© 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. 32798
    Prev
    Next
    INDEX
    Explanations

    references to specific units of time, particularly hours and days, as well as phrases related to work hours and schedules

    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
    +0.17
    0.7%
    481
    +0.14
    0.6%
    294
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    657
    +0.17
    0.14
    326
    +0.14
    0.21
    488
    +0.11
    0.14
    Negative Logits
    acted
    -0.92
    alore
    -0.89
    IFIC
    -0.84
    tarian
    -0.80
    iasis
    -0.77
    alach
    -0.76
    ãĥ´ãĤ¡
    -0.76
    ISON
    -0.76
    Reply
    -0.75
    dinand
    -0.72
    POSITIVE LOGITS
    pring
    1.19
    hift
    1.04
    peed
    1.02
    mith
    0.98
    pread
    0.98
     Ago
    0.96
    ourcing
    0.92
    pec
    0.90
    etting
    0.88
    heet
    0.88
    Activations Density 7.715%

    No Known Activations