© 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. 5511
    Prev
    Next
    INDEX
    Explanations

    text enclosed in quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    instances of parentheses or quotes that indicate citations or references

    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
    orate
    -0.67
     RC
    -0.66
     Marble
    -0.63
     Nunes
    -0.62
     Hodg
    -0.60
     Mills
    -0.60
     EVs
    -0.59
     ESV
    -0.59
     TTL
    -0.58
     Kin
    -0.58
    POSITIVE LOGITS
    catentry
    0.97
    wcsstore
    0.84
    pes
    0.77
    onduct
    0.74
    rag
    0.71
    ourage
    0.71
    pine
    0.70
    tnc
    0.69
    iquid
    0.67
    insula
    0.67
    Activations Density 0.019%

    No Known Activations