Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 8299
    Prev
    Next
    INDEX
    Explanations

    negative descriptive adjectives preceded by a hyphen

    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
    365
    +0.14
    0.6%
    314
    +0.13
    0.6%
    378
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.14
    0.04
    102
    +0.13
    0.04
    616
    +0.12
    0.04
    Negative Logits
     Dickinson
    -0.72
    çīĪ
    -0.71
     privately
    -0.71
    ulhu
    -0.69
     Sina
    -0.65
     Anon
    -0.65
     HHS
    -0.65
     ND
    -0.65
     Asia
    -0.64
     moder
    -0.64
    POSITIVE LOGITS
    sounding
    1.59
    looking
    1.54
    minded
    1.38
    enough
    1.30
    eyed
    1.25
    yet
    1.15
    ness
    1.13
    colored
    1.12
    footed
    1.07
    fe
    1.06
    Activations Density 0.057%

    No Known Activations