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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 25588
    Prev
    Next
    INDEX
    Explanations

    temperature values associated with cooking instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    230
    +0.11
    0.5%
    314
    +0.11
    0.5%
    495
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    230
    +0.11
    0.04
    507
    +0.11
    0.04
    260
    +0.11
    0.04
    Negative Logits
     kindred
    -0.66
     retrospective
    -0.62
    forth
    -0.62
     Gift
    -0.62
    alien
    -0.60
    folk
    -0.60
    reply
    -0.60
    ributed
    -0.58
     vain
    -0.58
     Painter
    -0.58
    POSITIVE LOGITS
     mph
    1.30
     degrees
    1.28
    °
    1.27
     rpm
    1.24
    mph
    1.21
     Hz
    1.12
    º
    1.12
    Hz
    1.10
     MPH
    1.09
    %.
    1.07
    Activations Density 0.071%

    No Known Activations