© 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. 18541
    Prev
    Next
    INDEX
    Explanations

    keywords related to computer programming and data processing, particularly focusing on terms related to output

    oai_token-act-pair · gpt-3.5-turbo

    references to output in a technical or programming context

    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
    creen
    -0.73
    ategory
    -0.68
     Antiqu
    -0.68
    ECK
    -0.67
     Blanc
    -0.66
    atural
    -0.65
    aps
    -0.64
    ormal
    -0.64
    erville
    -0.63
    anova
    -0.63
    POSITIVE LOGITS
    ted
    1.21
    ting
    1.16
     outputs
    0.86
     Output
    0.81
    Stream
    0.80
     output
    0.79
    output
    0.75
    ivity
    0.73
     streams
    0.73
     piping
    0.71
    Activations Density 0.021%

    No Known Activations