© 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. 2993
    Prev
    Next
    INDEX
    Explanations

    events or actions that lead to significant consequences or outcomes

    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
    164
    +0.11
    0.5%
    195
    +0.09
    0.4%
    21
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    164
    +0.11
    0.05
    21
    +0.09
    0.04
    541
    +0.09
    0.04
    Negative Logits
     mercy
    -0.63
    entric
    -0.61
     symmetry
    -0.60
    aves
    -0.60
    avorite
    -0.59
    arest
    -0.58
     loopholes
    -0.58
     Vaughn
    -0.57
    irlf
    -0.56
    afort
    -0.56
    POSITIVE LOGITS
    better
    0.95
    gers
    0.94
    ership
    0.81
    hunt
    0.77
    uez
    0.75
     nowhere
    0.74
    wig
    0.74
    ges
    0.74
    -+
    0.74
    bare
    0.72
    Activations Density 0.386%

    No Known Activations