© 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. 9205
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussions, mentions, or occurrences of different topics or themes

    oai_token-act-pair · gpt-3.5-turbo

    phrases or references that involve the concept of "talk" related to various topics

    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
     partName
    -0.70
    CG
    -0.62
    owner
    -0.62
    icum
    -0.61
     Cartoon
    -0.61
    omers
    -0.59
    iaries
    -0.59
    lahoma
    -0.59
    soever
    -0.58
     Tiff
    -0.58
    POSITIVE LOGITS
     sorts
    0.95
    enance
    0.93
     impending
    0.82
     abol
    0.76
    ãĢİ
    0.76
     horrors
    0.76
     doom
    0.76
     sidx
    0.71
     course
    0.70
     wanting
    0.69
    Activations Density 0.120%

    No Known Activations