© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 1597
    Prev
    Next
    INDEX
    Explanations

    phrases related to public availability or accessibility

    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
    503
    +0.15
    0.7%
    554
    +0.13
    0.6%
    288
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    554
    +0.15
    0.02
    112
    +0.13
    0.04
    151
    +0.12
    0.04
    Negative Logits
    nesota
    -0.94
    nian
    -0.77
    OPE
    -0.76
    lectic
    -0.76
    IER
    -0.70
    llan
    -0.68
    uel
    -0.67
     Benn
    -0.67
    ansas
    -0.67
    ners
    -0.67
    POSITIVE LOGITS
    ised
    0.99
     shaming
    0.96
     relations
    0.94
    ally
    0.91
     humiliation
    0.90
    isable
    0.86
    izing
    0.86
     outcry
    0.84
     feud
    0.84
    ising
    0.84
    Activations Density 0.040%

    No Known Activations