© 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. 18931
    Prev
    Next
    INDEX
    Explanations

    references to specific dates, events, and locations in news articles

    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
    640
    +0.18
    0.8%
    430
    +0.13
    0.6%
    145
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.18
    0.10
    640
    +0.13
    0.08
    430
    +0.11
    0.08
    Negative Logits
     imperson
    -0.85
     pretended
    -0.81
     lately
    -0.77
     pooled
    -0.77
     misplaced
    -0.76
     mistaken
    -0.75
    ¬¼
    -0.73
     melted
    -0.72
    pired
    -0.72
     disguise
    -0.71
    POSITIVE LOGITS
     Tickets
    1.16
     Meanwhile
    1.10
    Tickets
    1.09
     Until
    1.08
     Dates
    1.06
     Depending
    1.03
    <|endoftext|>
    1.02
     Assuming
    1.00
     Expect
    0.98
     Sources
    0.98
    Activations Density 0.354%

    No Known Activations