© 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. 5016
    Prev
    Next
    INDEX
    Explanations

    references to specific numerical values related to prices or costs

    oai_token-act-pair · gpt-3.5-turbo

    references to monetary costs and pricing information

    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
    ework
    -0.80
    idth
    -0.76
    ITED
    -0.69
     Dresden
    -0.68
     skelet
    -0.68
    adapt
    -0.67
    azel
    -0.65
     psychiat
    -0.63
    ãĤ¤ãĥĪ
    -0.62
    fell
    -0.62
    POSITIVE LOGITS
     cents
    1.18
     apiece
    1.05
     per
    0.88
     dollar
    0.87
     ($
    0.80
    clair
    0.79
     increments
    0.78
    renheit
    0.77
     sterling
    0.77
     (£
    0.75
    Activations Density 0.028%

    No Known Activations