© 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 12288
    9. 8-RES_FS12288-JB
    11. 9739
    Prev
    Next
    INDEX
    Explanations

    sentences related to critiques or discussions on various topics

    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
    507
    +0.10
    0.5%
    380
    +0.10
    0.5%
    217
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.10
    0.08
    720
    +0.10
    0.08
    546
    +0.10
    0.07
    Negative Logits
    STATE
    -0.70
    boro
    -0.68
     guiActiveUnfocused
    -0.68
    ews
    -0.66
    ../
    -0.66
    roup
    -0.66
    ahime
    -0.65
    ļéĨĴ
    -0.61
    pleted
    -0.61
    bris
    -0.60
    POSITIVE LOGITS
     however
    1.71
     moreover
    1.45
     meanwhile
    1.39
     though
    1.26
     alas
    1.22
     incidentally
    1.20
     huh
    1.12
     therefore
    1.10
     anyway
    1.05
     according
    1.04
    Activations Density 0.543%

    No Known Activations