© 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 12288
    9. 8-RES_FS12288-JB
    11. 9663
    Prev
    Next
    INDEX
    Explanations

    adjectives and phrases related to components and operation of a system

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    480
    +0.15
    0.7%
    75
    +0.10
    0.5%
    119
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.15
    0.06
    119
    +0.10
    0.05
    197
    +0.10
    0.05
    Negative Logits
    onde
    -0.71
    pta
    -0.71
    ilings
    -0.68
    arthed
    -0.66
    ãĥŃ
    -0.66
    appings
    -0.66
    sequent
    -0.64
    }}
    -0.64
    selected
    -0.63
    ]}
    -0.63
    POSITIVE LOGITS
     kinda
    0.86
     raining
    0.85
     irony
    0.79
     funny
    0.79
     coincidence
    0.75
     ironic
    0.75
     awfully
    0.73
     alot
    0.73
     pity
    0.73
     instinct
    0.72
    Activations Density 0.818%

    No Known Activations