© 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 3072
    9. 8-RES_FS3072-JB
    11. 2948
    Prev
    Next
    INDEX
    Explanations

    information related to a specific city."""

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    447
    +0.18
    0.8%
    481
    +0.14
    0.6%
    715
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.18
    0.15
    461
    +0.14
    0.13
    401
    +0.10
    0.15
    Negative Logits
    actionDate
    -0.73
    Ô
    -0.72
    Els
    -0.70
    piring
    -0.70
    cit
    -0.67
    Area
    -0.67
    Redd
    -0.66
    geries
    -0.66
    interstitial
    -0.65
    ģ«
    -0.65
    POSITIVE LOGITS
     opted
    1.19
     intends
    1.18
     responded
    1.16
     reacted
    1.13
     expects
    1.12
     insists
    1.10
     chose
    1.09
     maintains
    1.09
     retains
    1.09
     undertook
    1.08
    Activations Density 2.265%

    No Known Activations