© 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. 6-RES-JB
    11. 9328
    Prev
    Next
    INDEX
    Explanations

    terms related to specific names or places

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific location or entity named "Hind."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ynthesis
    -0.77
    è¦ļéĨĴ
    -0.77
    ãĥ¯
    -0.76
    76561
    -0.73
    ailability
    -0.70
    osponsors
    -0.70
    oker
    -0.68
    ãĤ£
    -0.67
    ylum
    -0.66
    isable
    -0.65
    POSITIVE LOGITS
    sight
    1.22
    ering
    1.00
    shire
    0.91
    rance
    0.88
    quarters
    0.87
    erella
    0.86
     Hind
    0.82
    nesses
    0.80
    say
    0.78
    ered
    0.75
    Activations Density 0.036%

    No Known Activations