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 24576
    5. 8-RES_FS24576-JB
    6. 18479
    Prev
    Next
    INDEX
    Explanations

    phrases related to confirmation and verification

    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
    215
    +0.10
    0.5%
    562
    +0.10
    0.5%
    202
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.10
    0.05
    55
    +0.10
    0.05
    512
    +0.10
    0.04
    Negative Logits
    marg
    -0.89
     incent
    -0.77
    istrates
    -0.76
     incentives
    -0.73
     frameworks
    -0.71
    Requires
    -0.71
    ieties
    -0.70
    Explore
    -0.70
    igent
    -0.70
     counselors
    -0.69
    POSITIVE LOGITS
     hoax
    0.96
     theirs
    0.92
     authentic
    0.92
     fake
    0.92
     yours
    0.91
     hers
    0.89
     genuine
    0.86
     actual
    0.86
     legit
    0.83
     ours
    0.81
    Activations Density 0.364%

    No Known Activations