© 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 EvalsExportsinterp-engineNEWAPI 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. 10420
    Prev
    Next
    INDEX
    Explanations

    keywords related to technology and production processes

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to creation and structure in various contexts

    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
    -0.71
    ©¶æ
    -0.63
    addons
    -0.63
     Volunte
    -0.62
     Grounds
    -0.61
     Paran
    -0.61
     Discord
    -0.60
     Bans
    -0.60
     precaution
    -0.58
    Gaming
    -0.57
    POSITIVE LOGITS
     indistinguishable
    0.86
     usable
    0.81
     lasting
    0.79
    uable
    0.79
    irable
    0.79
     instantly
    0.78
     equivalent
    0.75
     unlike
    0.74
     unparalleled
    0.74
     richer
    0.74
    Activations Density 0.649%

    No Known Activations