© 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. 9-RES-JB
    11. 1800
    Prev
    Next
    INDEX
    Explanations

    comparisons between different entities or scenarios

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases that highlight differences or similarities between entities or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Invalid
    -0.74
    iband
    -0.70
    wine
    -0.69
    Written
    -0.67
    mount
    -0.64
    he
    -0.64
    iverse
    -0.63
    arak
    -0.63
    breaker
    -0.63
    ANCE
    -0.62
    POSITIVE LOGITS
     other
    0.99
     contemporaries
    0.96
     peers
    0.95
     ours
    0.95
     others
    0.90
     previous
    0.88
     what
    0.88
     comparable
    0.83
     counterparts
    0.80
     alternatives
    0.79
    Activations Density 0.128%

    No Known Activations