© 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. 8-RES-JB
    11. 11641
    Prev
    Next
    INDEX
    Explanations

    phrases related to tasks or actions being done

    oai_token-act-pair · gpt-3.5-turbo

    references to social interactions or cooperation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pires
    -0.66
    DonaldTrump
    -0.58
     meets
    -0.58
    itates
    -0.57
     wors
    -0.56
    hovah
    -0.55
    —"
    -0.55
     guiName
    -0.55
    yip
    -0.54
    ulates
    -0.54
    POSITIVE LOGITS
    sequently
    1.05
    RESULTS
    0.97
     hindsight
    0.96
     remained
    0.94
    didn
    0.87
     consisted
    0.86
    was
    0.86
    Had
    0.83
     lacked
    0.82
     ended
    0.82
    Activations Density 1.439%

    No Known Activations