© 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. 9370
    Prev
    Next
    INDEX
    Explanations

    articles and reports within the context of a longer document

    oai_token-act-pair · gpt-3.5-turbo

    terms related to publications, reports, and research 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
    orsche
    -0.66
    itars
    -0.64
    ventus
    -0.62
    ofi
    -0.61
    uilt
    -0.56
     Reborn
    -0.56
    guyen
    -0.54
     liner
    -0.52
    ereo
    -0.52
    ifax
    -0.51
    POSITIVE LOGITS
    20439
    0.76
     describ
    0.63
    Materials
    0.59
    ="#
    0.57
     documenting
    0.57
     behold
    0.56
    Abstract
    0.55
     conclud
    0.53
     underest
    0.53
     describing
    0.51
    Activations Density 0.827%

    No Known Activations