© 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. 8-RES-JB
    11. 20255
    Prev
    Next
    INDEX
    Explanations

    references to clothing items or accessories, particularly suits

    oai_token-act-pair · gpt-3.5-turbo

    references to suits or legal contexts related to negotiation or business dealings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CTR
    -0.72
    eger
    -0.71
     VIDEOS
    -0.67
    raltar
    -0.63
     ultras
    -0.60
    JV
    -0.59
    prototype
    -0.58
    reference
    -0.57
    çīĪ
    -0.56
     Sabha
    -0.56
    POSITIVE LOGITS
    cases
    1.46
    ably
    1.37
    ability
    1.18
    ors
    0.98
    emate
    0.95
     jacket
    0.91
    case
    0.90
    suit
    0.89
    kat
    0.88
    MENTS
    0.85
    Activations Density 0.037%

    No Known Activations