Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 1233
    Prev
    Next
    INDEX
    Explanations

    phrases related to social justice and political activism

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    660
    +0.12
    0.6%
    656
    +0.10
    0.5%
    606
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    660
    +0.12
    0.04
    288
    +0.10
    0.04
    32
    +0.10
    0.04
    Negative Logits
    Prof
    -0.72
    PRES
    -0.72
    BuyableInstoreAndOnline
    -0.70
     Rica
    -0.68
    ACP
    -0.67
    ä¿
    -0.66
    arate
    -0.66
    Swe
    -0.64
    boa
    -0.64
    ?????-
    -0.63
    POSITIVE LOGITS
    est
    1.01
    liest
    0.96
    cients
    0.95
     masses
    0.94
     populace
    0.90
     ones
    0.86
    hest
    0.81
     flock
    0.78
     psyche
    0.77
     Greeks
    0.77
    Activations Density 0.174%

    No Known Activations