© 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 3072
    9. 8-RES_FS3072-JB
    11. 2984
    Prev
    Next
    INDEX
    Explanations

    historical and biographical information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    604
    +0.15
    0.7%
    314
    +0.12
    0.6%
    160
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    604
    +0.15
    0.08
    21
    +0.12
    0.05
    670
    +0.10
    0.05
    Negative Logits
     intensive
    -0.71
     manufact
    -0.66
     relations
    -0.65
     showdown
    -0.64
     volunte
    -0.63
     intermediate
    -0.62
     factories
    -0.62
     nearest
    -0.62
     cooperative
    -0.60
     collide
    -0.60
    POSITIVE LOGITS
    ...]
    1.43
    Pg
    1.38
    âĢ¦]
    1.34
    note
    1.19
    ?]
    1.10
    src
    1.06
    Footnote
    1.05
    sic
    0.97
    edit
    0.96
     citation
    0.95
    Activations Density 0.173%

    No Known Activations