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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 45459
    Prev
    Next
    INDEX
    Explanations

    adjectives that describe qualities or characteristics of items or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    361
    +0.10
    0.5%
    745
    +0.10
    0.4%
    320
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    707
    +0.10
    0.03
    588
    +0.10
    0.02
    737
    +0.09
    0.02
    Negative Logits
    emen
    -0.71
    ACY
    -0.67
    wick
    -0.65
    ĺħ
    -0.62
     Immun
    -0.60
    SON
    -0.60
    uctions
    -0.59
    CHAT
    -0.59
    ools
    -0.58
    umbai
    -0.58
    POSITIVE LOGITS
     than
    0.79
    idious
    0.74
    iera
    0.73
    iated
    0.72
     minded
    0.72
    minded
    0.70
    istic
    0.69
    isable
    0.69
     as
    0.68
     geographically
    0.68
    Activations Density 0.057%

    No Known Activations