© 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. 9-RES-JB
    6. 13523
    Prev
    Next
    INDEX
    Explanations

    keywords related to technology and digital platforms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to technology and online interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ones
    -0.70
     Sections
    -0.68
     Hog
    -0.60
     Highlander
    -0.60
    rarily
    -0.59
     Moz
    -0.59
     Hond
    -0.58
     Sed
    -0.57
     Toad
    -0.57
     Slug
    -0.56
    POSITIVE LOGITS
    mma
    0.83
    âĺ
    0.81
    eworld
    0.75
    [/
    0.68
    .?
    0.67
    ãĥ¯
    0.67
    ĸļ
    0.66
    .</
    0.64
    ylum
    0.64
    estyle
    0.62
    Activations Density 0.723%

    No Known Activations