© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 4775
    Prev
    Next
    INDEX
    Explanations

    web-related terms and phrases

    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
    +0.21
    0.8%
    167
    +0.17
    0.7%
    438
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.21
    0.37
    138
    +0.17
    0.35
    64
    +0.16
    -0.14
    Negative Logits
    士
    -0.86
     unfocusedRange
    -0.86
     Mori
    -0.82
     Clause
    -0.82
    xual
    -0.81
     Lauder
    -0.81
     Cla
    -0.78
    ividual
    -0.78
    Downloadha
    -0.78
     retali
    -0.75
    POSITIVE LOGITS
    inar
    1.36
    pages
    1.26
    izen
    1.21
     browsers
    1.16
    masters
    1.15
    browser
    1.13
    bing
    1.09
    Socket
    1.08
    master
    1.08
     browser
    1.04
    Activations Density 7.672%

    No Known Activations