© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 7261
    Prev
    Next
    INDEX
    Explanations

    terms related to physics and cosmology theories

    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
    81
    +0.11
    0.5%
    278
    +0.11
    0.5%
    82
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    81
    +0.11
    0.05
    171
    +0.11
    0.04
    363
    +0.09
    0.04
    Negative Logits
    ————————
    -0.63
    ARR
    -0.61
    â̦â̦â̦â̦â̦â̦â̦â̦
    -0.59
    !?
    -0.57
    ¶
    -0.55
    ________________________________
    -0.55
    cmp
    -0.55
    />
    -0.54
    Official
    -0.54
    ###
    -0.54
    POSITIVE LOGITS
    etheless
    0.70
    foundland
    0.67
     coasts
    0.67
     Fortune
    0.58
    cession
    0.57
    soDeliveryDate
    0.57
     Reps
    0.57
     ling
    0.55
    zyme
    0.54
     gloss
    0.54
    Activations Density 0.290%

    No Known Activations