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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 19388
    Prev
    Next
    INDEX
    Explanations

    words related to initial actions or plans

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "initially"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rf
    -0.85
     Vish
    -0.74
    holes
    -0.70
    yers
    -0.70
    gerald
    -0.69
     Chef
    -0.68
    rom
    -0.68
    nce
    -0.68
    masters
    -0.67
    laws
    -0.66
    POSITIVE LOGITS
     blush
    0.88
     responders
    0.86
     unden
    0.84
     stages
    0.83
     initialized
    0.82
     withd
    0.80
     exting
    0.79
     solic
    0.78
     conclud
    0.78
     notor
    0.77
    Activations Density 0.010%

    No Known Activations