© 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 49152
    9. 8-RES_FS49152-JB
    11. 37322
    Prev
    Next
    INDEX
    Explanations

    phrases related to explanations and justifications

    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
    195
    +0.12
    0.6%
    239
    +0.12
    0.5%
    759
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    239
    +0.12
    0.02
    195
    +0.12
    0.01
    759
    +0.10
    0.02
    Negative Logits
    sembly
    -0.80
    ngth
    -0.79
    ille
    -0.75
     shalt
    -0.69
    Ranked
    -0.69
    opers
    -0.65
    field
    -0.63
    emies
    -0.62
    net
    -0.61
    kai
    -0.61
    POSITIVE LOGITS
     why
    1.35
    why
    1.09
     WHY
    1.07
     discrepancies
    0.86
     how
    0.83
    Origin
    0.82
     inconsistencies
    0.82
     explanations
    0.79
     mysteries
    0.74
     away
    0.72
    Activations Density 0.025%

    No Known Activations