© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 26672
    Prev
    Next
    INDEX
    Explanations

    names, particularly those associated with political figures and events

    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
    527
    +0.09
    0.4%
    730
    +0.09
    0.4%
    699
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    730
    +0.09
    0.01
    326
    +0.09
    0.01
    99
    +0.09
    0.01
    Negative Logits
    iances
    -0.70
    icals
    -0.64
     photon
    -0.64
     Covenant
    -0.63
    ãĥĩãĤ£
    -0.60
     variance
    -0.60
     Lantern
    -0.58
    oubted
    -0.58
    iqueness
    -0.57
     surn
    -0.57
    POSITIVE LOGITS
    lette
    1.15
    au
    0.96
    ff
    0.94
    vous
    0.92
    lett
    0.87
    lete
    0.86
    grad
    0.85
    lect
    0.85
    tti
    0.80
    ugal
    0.80
    Activations Density 0.006%

    No Known Activations