Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 8409
    Prev
    Next
    INDEX
    Explanations

    adjectives related to visual attributes, such as colors or appearances

    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
    123
    +0.13
    0.6%
    515
    +0.12
    0.5%
    670
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.06
    455
    +0.12
    0.05
    123
    +0.11
    0.04
    Negative Logits
     VIDEOS
    -0.87
    eah
    -0.71
    Shot
    -0.70
     Carlson
    -0.69
    thal
    -0.69
    externalActionCode
    -0.68
    OHN
    -0.67
     Dull
    -0.66
     Russo
    -0.65
    cler
    -0.65
    POSITIVE LOGITS
    £
    1.03
     Whilst
    0.93
    uminium
    0.90
     analyse
    0.88
     programmes
    0.86
    piece
    0.84
     defences
    0.84
     Firstly
    0.84
     aluminium
    0.82
    colour
    0.81
    Activations Density 0.378%

    No Known Activations