© 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 768
    9. 8-RES_FS768-JB
    11. 665
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of openness, specifically in terms of software and ideas

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    246
    +0.11
    0.5%
    240
    +0.10
    0.4%
    726
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    240
    +0.11
    0.08
    665
    +0.10
    0.09
    246
    +0.09
    0.08
    Negative Logits
    iage
    -0.76
    CTV
    -0.72
    rior
    -0.65
     endors
    -0.63
    ãĥīãĥ©ãĤ´ãĥ³
    -0.62
    grade
    -0.61
     Commando
    -0.59
    doms
    -0.59
     Avg
    -0.57
     constitu
    -0.56
    POSITIVE LOGITS
     doors
    1.04
     Doors
    1.03
    office
    0.87
    ource
    0.85
     wounds
    0.84
     eyed
    0.83
     loopholes
    0.82
     pores
    0.82
     door
    0.80
     portals
    0.79
    Activations Density 3.728%

    No Known Activations