© 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. 2980
    Prev
    Next
    INDEX
    Explanations

    phrases related to passing or happening of events

    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
    98
    +0.12
    0.6%
    715
    +0.10
    0.5%
    521
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    98
    +0.12
    0.10
    715
    +0.10
    0.08
    446
    +0.09
    0.07
    Negative Logits
    ©¶æ¥µ
    -0.76
    ÃįÃį
    -0.74
    folios
    -0.71
    Afee
    -0.67
    ãĥķ
    -0.65
     Annotations
    -0.65
    NetMessage
    -0.64
     Volunteers
    -0.63
    GROUND
    -0.63
    \">
    -0.62
    POSITIVE LOGITS
     succeeds
    0.95
     succeed
    0.91
     fails
    0.89
     someday
    0.87
     properly
    0.85
     somehow
    0.82
     sufficiently
    0.82
     ever
    0.78
     correctly
    0.73
    pires
    0.71
    Activations Density 1.526%

    No Known Activations