© 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. 0-RES-JB
    11. 15297
    Prev
    Next
    INDEX
    Explanations

    proper nouns or terms related to a specific person named Cond

    oai_token-act-pair · gpt-3.5-turbo

    mentions of conditions or states associated with organized groups or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agy
    -0.97
     hops
    -0.74
    YE
    -0.74
     athlet
    -0.73
     unlocking
    -0.68
     beet
    -0.68
     unlock
    -0.67
    OSH
    -0.67
     da
    -0.67
     wizard
    -0.66
    POSITIVE LOGITS
     Cond
    3.96
    Cond
    2.82
    cond
    2.22
     cond
    1.94
     condom
    1.14
     condensed
    1.09
     condo
    1.08
     condoms
    1.07
     condos
    1.06
     conduit
    1.02
    Activations Density 0.038%

    No Known Activations