© 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. 18804
    Prev
    Next
    INDEX
    Explanations

    ages mentioned in the text

    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
    383
    +0.11
    0.5%
    347
    +0.10
    0.5%
    321
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    347
    +0.11
    0.02
    603
    +0.10
    0.02
    383
    +0.10
    0.02
    Negative Logits
    edia
    -0.80
    vous
    -0.76
    aptic
    -0.76
    pmwiki
    -0.75
    aminer
    -0.74
    odium
    -0.74
    atari
    -0.74
     Bundy
    -0.73
    vernment
    -0.72
    ossom
    -0.71
    POSITIVE LOGITS
     18
    0.88
     19
    0.88
     21
    0.81
     14
    0.79
    BuyableInstoreAndOnline
    0.79
     23
    0.78
     13
    0.78
     22
    0.77
     53
    0.77
     29
    0.75
    Activations Density 0.020%

    No Known Activations