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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 69
    Prev
    Next
    INDEX
    Explanations

    words related to signs or indications

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    679
    +0.14
    0.6%
    114
    +0.10
    0.5%
    182
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    114
    +0.14
    0.03
    341
    +0.10
    0.02
    182
    +0.10
    0.02
    Negative Logits
    iband
    -0.72
    ĸļ
    -0.70
    ategory
    -0.68
     fixme
    -0.67
     Remastered
    -0.67
    ulu
    -0.66
    IRO
    -0.66
     DRAG
    -0.66
     inh
    -0.64
     swaps
    -0.64
    POSITIVE LOGITS
    atories
    1.36
    posts
    1.29
    post
    1.14
    posted
    1.11
    atory
    1.07
    orial
    0.98
    alled
    0.97
    ifier
    0.97
    ifiers
    0.96
    ging
    0.91
    Activations Density 0.040%

    No Known Activations