© 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. 7-RES-JB
    11. 17156
    Prev
    Next
    INDEX
    Explanations

    words related to act of slowing down or pausing, often with a negative connotation

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with errors, missteps, and problems in various contexts

    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
     Sorceress
    -0.74
     Museum
    -0.71
     Prophet
    -0.70
     Library
    -0.68
     Raider
    -0.66
     Duchess
    -0.65
     Emir
    -0.65
     Mistress
    -0.62
     Symphony
    -0.62
     Lair
    -0.61
    POSITIVE LOGITS
    anging
    0.99
    reating
    0.98
    inging
    0.97
    ashing
    0.96
    ailing
    0.95
    ipping
    0.94
    aging
    0.93
    iddling
    0.93
    isting
    0.92
    aring
    0.92
    Activations Density 0.381%

    No Known Activations