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

    Neuronpedia

    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. 6-RES-JB
    11. 16856
    Prev
    Next
    INDEX
    Explanations

    strong verbs or action-oriented words

    oai_token-act-pair · gpt-3.5-turbo

    prominent verbs indicating actions, possibilities, and conditions

    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
     Templ
    -0.70
     Deity
    -0.65
    ordinary
    -0.64
    inas
    -0.63
     Practices
    -0.62
    Div
    -0.61
    chapter
    -0.60
    Purchase
    -0.59
    Wonder
    -0.57
    Zone
    -0.57
    POSITIVE LOGITS
     however
    0.80
     therefore
    0.73
     culmin
    0.70
     consist
    0.69
     consisted
    0.68
     varied
    0.67
     thus
    0.64
     acronym
    0.64
     furthermore
    0.63
     lasted
    0.61
    Activations Density 0.581%

    No Known Activations