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. 12057
    Prev
    Next
    INDEX
    Explanations

    descriptions and discussions related to various topics, ranging from arts and culture to political and societal issues

    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
    480
    +0.51
    2.6%
    266
    +0.13
    0.6%
    598
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.51
    0.01
    266
    +0.13
    0.10
    195
    +0.10
    0.02
    Negative Logits
    but
    -0.67
    schild
    -0.63
    bowl
    -0.61
    $$$$
    -0.60
    orie
    -0.58
     but
    -0.57
     ILCS
    -0.56
    代
    -0.55
    alde
    -0.55
     But
    -0.55
    POSITIVE LOGITS
     nonetheless
    1.41
    etheless
    1.11
     nevertheless
    1.08
     strangely
    0.65
     still
    0.65
     undeniable
    0.64
     overshadowed
    0.63
     awfully
    0.62
     cautioned
    0.62
     overlooked
    0.61
    Activations Density 1.216%

    No Known Activations