© 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. 6-RES-JB
    11. 9732
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific terms mentioned in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to significant topics or concepts in the discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soever
    -0.77
     Mehran
    -0.68
     Canad
    -0.63
     Madden
    -0.63
     Oliv
    -0.62
    IRO
    -0.61
    hops
    -0.61
    liam
    -0.59
     breathed
    -0.58
     Brenda
    -0.58
    POSITIVE LOGITS
     possibility
    1.07
     similarities
    0.93
     importance
    0.93
     specificity
    0.91
     plight
    0.85
     possibilities
    0.85
     caveat
    0.83
     dangers
    0.83
     shortcomings
    0.81
     seriousness
    0.81
    Activations Density 0.291%

    No Known Activations