© 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. 35154
    Prev
    Next
    INDEX
    Explanations

    number combinations that match specific patterns

    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
    +0.18
    0.9%
    649
    +0.12
    0.6%
    659
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.18
    0.07
    640
    +0.12
    0.14
    210
    +0.12
    0.04
    Negative Logits
    zona
    -0.65
    terday
    -0.60
     Adin
    -0.59
     diapers
    -0.59
    Ø©
    -0.57
    ãĥ³ãĤ¸
    -0.56
    ÙĴ
    -0.56
    purpose
    -0.54
    wcsstore
    -0.54
    cipl
    -0.54
    POSITIVE LOGITS
    orea
    1.05
    laus
    1.01
    EEP
    0.99
    ernel
    0.99
    irk
    0.97
    eeper
    0.96
    rieg
    0.93
    essel
    0.92
    won
    0.86
    istani
    0.86
    Activations Density 6.866%

    No Known Activations