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 12288
    5. 8-RES_FS12288-JB
    6. 10030
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific phrases related to historical, academic, or cultural contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    284
    +0.11
    0.5%
    648
    +0.11
    0.5%
    572
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    251
    +0.11
    0.06
    18
    +0.11
    0.07
    167
    +0.10
    0.01
    Negative Logits
    imately
    -0.79
    theless
    -0.74
    appropriately
    -0.73
    ivably
    -0.69
    ifully
    -0.68
    ificantly
    -0.68
     grossly
    -0.67
    Effective
    -0.66
    volent
    -0.66
     curiously
    -0.65
    POSITIVE LOGITS
    stros
    0.82
    izen
    0.82
    hander
    0.79
    anse
    0.78
    agonist
    0.76
    tick
    0.74
    ilib
    0.74
    aviour
    0.70
    ahime
    0.70
    ainment
    0.69
    Activations Density 0.983%

    No Known Activations