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

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 23960
    Prev
    Next
    INDEX
    Explanations

    non-specific ordinal terms denoting ranks or positions

    oai_token-act-pair · gpt-3.5-turbo

    instances of phrases or words indicating hierarchy or priority

    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
    xit
    -0.50
     occup
    -0.44
    ussia
    -0.43
     intercepted
    -0.43
     mobilization
    -0.42
     SAM
    -0.42
     conversion
    -0.42
     conversions
    -0.42
     prost
    -0.42
     unlaw
    -0.41
    POSITIVE LOGITS
    hap
    0.67
    etheless
    0.61
    ½
    0.57
    ¤
    0.56
    oiler
    0.56
    onda
    0.55
    £
    0.53
    Nonetheless
    0.53
    arc
    0.52
     furthermore
    0.52
    Activations Density 0.804%

    No Known Activations