© 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. 9637
    Prev
    Next
    INDEX
    Explanations

    phrases where something or someone is being evaluated or judged as having a particular status or characteristic

    oai_token-act-pair · gpt-3.5-turbo

    statements that involve the act of being regarded or labeled in a certain way

    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
    inas
    -0.68
    hire
    -0.67
    brow
    -0.64
    sheets
    -0.63
    load
    -0.62
    loads
    -0.62
    letter
    -0.61
    arling
    -0.60
     Herrera
    -0.59
    Ring
    -0.59
    POSITIVE LOGITS
    phas
    0.95
     favorably
    0.91
     Tradable
    0.84
     infall
    0.74
     expend
    0.73
     canon
    0.73
    soDeliveryDate
    0.71
     considered
    0.71
     "$:/
    0.71
     cel
    0.71
    Activations Density 0.030%

    No Known Activations