© 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 EvalsExportsAPI 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. 3874
    Prev
    Next
    INDEX
    Explanations

    terms related to specific quantities and measurements

    oai_token-act-pair · gpt-3.5-turbo

    quantitative measurements or data points in various contexts

    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
    vice
    -0.62
    aband
    -0.60
    ãĥĩãĤ£
    -0.58
    manent
    -0.58
    ties
    -0.57
    sth
    -0.56
     mush
    -0.56
    ="#
    -0.55
     Malays
    -0.53
    KING
    -0.53
    POSITIVE LOGITS
     respectively
    1.62
     depending
    0.86
     alike
    0.85
    depending
    0.82
     combined
    0.81
    +.
    0.80
     respective
    0.80
     =================================
    0.72
    estic
    0.71
     etc
    0.71
    Activations Density 0.302%

    No Known Activations