© 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. 13595
    Prev
    Next
    INDEX
    Explanations

    actions related to software and customization

    oai_token-act-pair · gpt-3.5-turbo

    commands related to software installation and configuration

    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
    Defense
    -0.67
    é¾įå¥ij士
    -0.65
    BuyableInstoreAndOnline
    -0.61
     endeavour
    -0.59
    eded
    -0.59
    los
    -0.58
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.58
    capacity
    -0.58
    rium
    -0.58
    glas
    -0.55
    POSITIVE LOGITS
     yourself
    1.14
     yourselves
    0.97
    ivably
    0.93
     anytime
    0.91
     your
    0.89
     unlimited
    0.87
     anywhere
    0.87
     Yourself
    0.86
     manually
    0.81
     whatever
    0.79
    Activations Density 0.354%

    No Known Activations