© 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. 1665
    Prev
    Next
    INDEX
    Explanations

    references to newsletters and subscription options

    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
    643
    +0.12
    0.5%
    496
    +0.10
    0.5%
    51
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    257
    +0.12
    0.02
    568
    +0.10
    0.02
    117
    +0.09
    0.02
    Negative Logits
    etts
    -0.70
    é¾įå¥ij士
    -0.63
    lain
    -0.61
     Aber
    -0.59
     Âł Âł
    -0.59
     Hann
    -0.58
     aqu
    -0.56
     contention
    -0.56
     circumst
    -0.56
    techn
    -0.55
    POSITIVE LOGITS
    ificate
    0.80
    apy
    0.76
    APD
    0.68
    leans
    0.68
    ktop
    0.65
    erity
    0.64
    NPR
    0.63
     Travels
    0.61
     Intellectual
    0.59
    akespeare
    0.59
    Activations Density 0.023%

    No Known Activations