© 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. 2986
    Prev
    Next
    INDEX
    Explanations

    references to legal rulings and contracts

    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
    481
    +0.55
    4.1%
    447
    +0.44
    3.3%
    373
    +0.32
    2.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.55
    0.30
    373
    +0.44
    -0.21
    562
    +0.32
    0.06
    Negative Logits
     thereof
    -0.49
     thereto
    -0.48
    =]
    -0.46
     guiActiveUnfocused
    -0.44
    eaturing
    -0.40
    ocre
    -0.39
    sequently
    -0.39
    itol
    -0.38
    sic
    -0.38
    itary
    -0.37
    POSITIVE LOGITS
     Canaver
    0.59
     Tsarnaev
    0.43
     Scientology
    0.41
     Guant
    0.41
     Arpaio
    0.39
     Nunes
    0.37
     Manson
    0.36
     MacArthur
    0.36
     Kafka
    0.36
     Trump
    0.35
    Activations Density 9.690%

    No Known Activations