© 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 24576
    9. 8-RES_FS24576-JB
    11. 9261
    Prev
    Next
    INDEX
    Explanations

    verbs related to chasing and stalking

    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
    326
    +0.13
    0.6%
    269
    +0.12
    0.5%
    549
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    269
    +0.13
    0.02
    326
    +0.12
    0.01
    271
    +0.09
    0.01
    Negative Logits
    galitarian
    -0.79
    animous
    -0.73
    ionic
    -0.72
    ition
    -0.66
    uben
    -0.66
    imating
    -0.65
    icum
    -0.65
     disproportion
    -0.65
    ickson
    -0.64
    requisite
    -0.64
    POSITIVE LOGITS
    crow
    0.84
     chase
    0.82
     Phant
    0.79
     prey
    0.73
    ========
    0.72
    ttes
    0.70
    =-=-=-=-=-=-=-=-
    0.70
    backs
    0.69
    rily
    0.69
     hikers
    0.68
    Activations Density 0.036%

    No Known Activations