© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 21191
    Prev
    Next
    INDEX
    Explanations

    instances where the text suggests the presence of a specific issue or matter needing attention or resolution

    oai_token-act-pair · gpt-3.5-turbo

    statements indicating the existence or occurrence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chains
    -0.69
    iaries
    -0.68
     predecessors
    -0.64
     segments
    -0.63
    ilst
    -0.62
    verse
    -0.61
    nels
    -0.61
     receipt
    -0.60
     heels
    -0.60
     earners
    -0.59
    POSITIVE LOGITS
     happening
    1.03
     transpired
    0.77
     forgiven
    0.74
    missing
    0.73
     wrong
    0.72
     gonna
    0.71
     done
    0.71
     bothering
    0.70
     going
    0.69
     cov
    0.69
    Activations Density 0.119%

    No Known Activations