© 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. 7414
    Prev
    Next
    INDEX
    Explanations

    second person pronouns

    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
    270
    +0.12
    0.5%
    383
    +0.12
    0.5%
    156
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    49
    +0.12
    0.06
    502
    +0.12
    0.05
    383
    +0.10
    0.06
    Negative Logits
     Grav
    -0.64
     Ashe
    -0.63
     Correction
    -0.60
    atoes
    -0.60
    acular
    -0.60
     Absent
    -0.60
     Amendments
    -0.59
     Eag
    -0.59
     Klu
    -0.59
     Canaver
    -0.58
    POSITIVE LOGITS
    're
    1.58
    've
    1.45
    'll
    1.11
     intend
    1.10
    'd
    1.05
     want
    1.05
    RS
    1.04
     wanna
    0.99
    tub
    0.96
     wish
    0.92
    Activations Density 0.144%

    No Known Activations