© 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. 7-RES-JB
    11. 13347
    Prev
    Next
    INDEX
    Explanations

    computer-related terms or keywords

    oai_token-act-pair · gpt-3.5-turbo

    technical specifications and data-related terms

    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
    eus
    -0.97
    urat
    -0.79
    orsi
    -0.77
    milo
    -0.75
    itness
    -0.73
    rists
    -0.65
    vice
    -0.65
     successors
    -0.65
    ichever
    -0.64
    ESCO
    -0.64
    POSITIVE LOGITS
    Requirements
    0.69
     Lod
    0.68
    ////
    0.66
     Paste
    0.62
    LOD
    0.62
    rawdownloadcloneembedreportprint
    0.61
    Chapter
    0.61
     Mehran
    0.60
     Chapter
    0.60
     Miscellaneous
    0.60
    Activations Density 0.074%

    No Known Activations