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

    Neuronpedia

    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. 3131
    Prev
    Next
    INDEX
    Explanations

    information about amendments or original versions of articles, statements, or content

    oai_token-act-pair · gpt-3.5-turbo
    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
    rouse
    -0.67
    otic
    -0.66
    Dialogue
    -0.63
     anymore
    -0.63
    oyle
    -0.63
    arta
    -0.62
     antioxid
    -0.62
    bys
    -0.60
    erno
    -0.60
    arms
    -0.59
    POSITIVE LOGITS
    hes
    1.17
     originally
    1.08
    wolves
    0.95
     instrumental
    0.91
     born
    0.91
     supposed
    0.87
     able
    0.86
    hers
    0.86
     previously
    0.86
     formerly
    0.83
    Activations Density 0.337%

    No Known Activations