© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 10241
    Prev
    Next
    INDEX
    Explanations

    numbers related to quantities or quantities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "and", indicating a focus on conjunctions or connections between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ADVERTISEMENT
    -0.79
    CHAT
    -0.75
    natureconservancy
    -0.74
    actionDate
    -0.74
    Phys
    -0.72
    Planet
    -0.68
    Deal
    -0.68
    Versions
    -0.67
    speech
    -0.67
    è»
    -0.66
    POSITIVE LOGITS
     onwards
    1.01
     then
    1.00
     thus
    0.93
     therefore
    0.92
     consequently
    0.91
     optionally
    0.89
     thereby
    0.87
     hence
    0.87
     thence
    0.86
     preferably
    0.85
    Activations Density 0.314%

    No Known Activations