© 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. 1563
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and sound engineering

    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
    373
    +0.14
    0.6%
    690
    +0.11
    0.5%
    460
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.14
    0.03
    690
    +0.11
    0.03
    4
    +0.11
    0.03
    Negative Logits
    orporated
    -0.66
    idas
    -0.61
    comed
    -0.60
    boro
    -0.60
    HUD
    -0.58
     Anchorage
    -0.57
     Haley
    -0.57
    STEM
    -0.56
    ACP
    -0.55
    HK
    -0.55
    POSITIVE LOGITS
    tains
    0.71
     htt
    0.70
     medicine
    0.67
    urated
    0.67
    ears
    0.66
     Ruin
    0.66
    oming
    0.65
    oscopic
    0.64
    lege
    0.64
    onet
    0.63
    Activations Density 0.082%

    No Known Activations