© 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. 9712
    Prev
    Next
    INDEX
    Explanations

    terms related to coding and programming languages

    oai_token-act-pair · gpt-3.5-turbo

    references to "DJANGO" or related content

    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
    20439
    -0.78
     GOODMAN
    -0.68
     Bened
    -0.67
    CLASSIFIED
    -0.66
     Caleb
    -0.63
     Jess
    -0.63
     Fifth
    -0.62
     cle
    -0.61
     LAT
    -0.59
     Donna
    -0.59
    POSITIVE LOGITS
    aughed
    0.78
    ucer
    0.73
    ifle
    0.71
    outed
    0.69
    iann
    0.69
    ynes
    0.68
    agne
    0.66
    senal
    0.66
    hovah
    0.65
    eto
    0.65
    Activations Density 0.297%

    No Known Activations