© 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. 6790
    Prev
    Next
    INDEX
    Explanations

    code syntax elements and specific programming words

    oai_token-act-pair · gpt-3.5-turbo

    programming constructs and structures, particularly relating to roles and function definitions

    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
    ensibly
    -0.76
    agna
    -0.64
    urion
    -0.63
    etsy
    -0.62
    itzer
    -0.62
     relics
    -0.60
    KI
    -0.60
    offensive
    -0.59
    senal
    -0.59
    çĶ°
    -0.58
    POSITIVE LOGITS
    else
    1.02
     }
    1.02
     };
    0.97
     Similarly
    0.96
     Alternatively
    0.95
    Output
    0.95
     ;;
    0.92
     &&
    0.92
     //[
    0.91
     ==
    0.90
    Activations Density 0.118%

    No Known Activations