© 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. 18808
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal issues or criticisms

    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
    123
    +0.12
    0.5%
    608
    +0.11
    0.5%
    766
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    123
    +0.12
    0.09
    469
    +0.11
    0.07
    29
    +0.09
    0.08
    Negative Logits
    CLASSIFIED
    -0.73
    mask
    -0.64
    TIME
    -0.64
    ALSE
    -0.63
     %%
    -0.61
    PLAY
    -0.61
     lasted
    -0.60
    ATURES
    -0.60
    #$
    -0.60
    FIG
    -0.60
    POSITIVE LOGITS
     favor
    1.53
     favour
    1.34
     lieu
    1.29
     order
    1.19
    efficiency
    1.15
     spite
    1.15
     vitro
    1.11
     accordance
    1.11
    effic
    1.11
     anticipation
    1.03
    Activations Density 0.336%

    No Known Activations