© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 17904
    Prev
    Next
    INDEX
    Explanations

    handwritten or inscribed text

    oai_token-act-pair · gpt-3.5-turbo

    references to different forms of writing or marking

    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
    EStreamFrame
    -0.87
    kus
    -0.86
    roxy
    -0.80
    asion
    -0.77
    nels
    -0.73
    iland
    -0.72
    Kin
    -0.71
    vati
    -0.71
    gart
    -0.71
    ecast
    -0.71
    POSITIVE LOGITS
     engraved
    1.14
     markings
    1.13
     handwriting
    1.11
     etched
    1.10
     scrib
    1.08
    prints
    1.08
     letters
    1.08
     handwritten
    1.07
     inscription
    1.07
     printed
    1.00
    Activations Density 0.140%

    No Known Activations