© 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. 9494
    Prev
    Next
    INDEX
    Explanations

    years in the early 1990s

    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
    246
    +0.10
    0.5%
    455
    +0.10
    0.4%
    218
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    18
    +0.10
    0.03
    337
    +0.10
    0.03
    669
    +0.09
    0.03
    Negative Logits
    edIn
    -0.79
    avorite
    -0.77
    oppable
    -0.69
    osate
    -0.69
    IDA
    -0.67
     chained
    -0.66
    iscopal
    -0.66
    Compat
    -0.64
     Disorder
    -0.64
    cham
    -0.63
    POSITIVE LOGITS
     twenties
    1.14
     stages
    1.10
     1980
    1.06
     1990
    1.05
    ixties
    1.04
     1970
    1.00
     1960
    1.00
     days
    0.99
     phases
    0.98
     2000
    0.98
    Activations Density 0.040%

    No Known Activations