© 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. 311
    Prev
    Next
    INDEX
    Explanations

    names of individual people or characters

    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
    481
    +0.21
    1.0%
    314
    +0.16
    0.7%
    140
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.21
    0.07
    314
    +0.16
    0.00
    140
    +0.11
    0.06
    Negative Logits
    opausal
    -0.87
    icably
    -0.77
     accomp
    -0.68
     concess
    -0.68
    merce
    -0.66
     conflic
    -0.66
     unnecess
    -0.65
     normative
    -0.65
    icable
    -0.65
    etheless
    -0.64
    POSITIVE LOGITS
    ings
    1.21
    able
    1.10
    down
    1.10
    downs
    1.04
    breaker
    1.03
    masters
    1.01
    back
    1.00
    ables
    0.99
    stick
    0.98
    away
    0.97
    Activations Density 0.509%

    No Known Activations