© 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 49152
    9. 8-RES_FS49152-JB
    11. 37277
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic and environmental conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    614
    +0.11
    0.5%
    338
    +0.11
    0.5%
    447
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.11
    0.02
    517
    +0.11
    0.02
    460
    +0.11
    0.02
    Negative Logits
    wered
    -0.81
    inav
    -0.79
    irs
    -0.69
    ads
    -0.69
    myra
    -0.68
    tein
    -0.67
    opes
    -0.66
    inka
    -0.65
    itars
    -0.65
    sight
    -0.65
    POSITIVE LOGITS
     conducive
    1.26
     environment
    0.88
     fost
    0.84
     wherein
    0.81
     rife
    0.79
     favorable
    0.78
     unfavorable
    0.77
     perv
    0.76
     atmosphere
    0.75
     prev
    0.72
    Activations Density 0.032%

    No Known Activations