© 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. 1375
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to political figures and locations

    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
    447
    +0.15
    0.7%
    481
    +0.13
    0.6%
    145
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    224
    +0.15
    0.07
    15
    +0.13
    0.07
    146
    +0.11
    0.05
    Negative Logits
    ]=
    -0.70
    Wr
    -0.70
     phased
    -0.61
     bites
    -0.60
     proportion
    -0.59
    Ö¼
    -0.59
    must
    -0.59
    UCK
    -0.59
    ]}
    -0.58
    phas
    -0.57
    POSITIVE LOGITS
     representatives
    0.84
    ilaterally
    0.80
     counterparts
    0.77
     whom
    0.73
     acquaintances
    0.72
    omever
    0.72
     backstage
    0.71
     colleagues
    0.71
     beforehand
    0.69
    friends
    0.69
    Activations Density 0.730%

    No Known Activations