© 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. 8-RES-JB
    11. 6963
    Prev
    Next
    INDEX
    Explanations

    single-letter detections located within a word

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of an empty or blank text segment

    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
     Angus
    -0.69
     Emerson
    -0.69
     appointments
    -0.67
     Allied
    -0.66
     Mellon
    -0.66
     Eag
    -0.65
     Borders
    -0.63
     Jagu
    -0.63
     Osh
    -0.62
     Clarkson
    -0.61
    POSITIVE LOGITS
    cess
    0.87
    sexual
    0.85
    ria
    0.85
    lex
    0.83
    vec
    0.83
    ird
    0.81
    lder
    0.81
     guest
    0.80
     ][
    0.80
    ctors
    0.75
    Activations Density 0.053%

    No Known Activations