© 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. 4843
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a transition or shift in focus within a text

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "where" indicating specific points or conditions in a discussion

    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
    rn
    -0.68
    jad
    -0.64
    ographed
    -0.63
    ãĥ´
    -0.62
    dayName
    -0.62
    opsy
    -0.61
    978
    -0.60
     independently
    -0.60
    ãĥı
    -0.59
    ograp
    -0.59
    POSITIVE LOGITS
     things
    1.01
     similarities
    0.72
     Leh
    0.72
     tensions
    0.71
     tragedy
    0.69
     trouble
    0.68
     Obi
    0.68
     tragedies
    0.67
     reckoning
    0.63
     discussions
    0.62
    Activations Density 0.078%

    No Known Activations