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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 19470
    Prev
    Next
    INDEX
    Explanations

    HTML tags related to webpage structure

    oai_token-act-pair · gpt-3.5-turbo

    HTML elements and attributes

    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
    ĪĴ
    -0.80
     tremend
    -0.72
    76561
    -0.65
     humid
    -0.64
    lé
    -0.63
    ©¶æ
    -0.63
     Miracle
    -0.63
     bluff
    -0.60
     dumps
    -0.60
     Lovecraft
    -0.59
    POSITIVE LOGITS
    ></
    1.53
    ><
    1.42
    >
    1.37
    >,
    1.31
    >:
    1.22
    >)
    1.21
    >"
    1.17
    ][/
    1.14
    >.
    1.13
    >>\
    1.13
    Activations Density 0.018%

    No Known Activations