© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7851
    Prev
    Next
    INDEX
    Explanations

    words related to size, dimensions, and measurements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to scale, range, or dimensions

    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
    iolet
    -0.68
    akia
    -0.66
    ificant
    -0.66
    arna
    -0.66
    ãĤĵ
    -0.66
    ongo
    -0.64
    ara
    -0.62
    mingham
    -0.59
    atto
    -0.57
    rosso
    -0.56
    POSITIVE LOGITS
    same
    0.85
     specified
    0.80
     mentioned
    0.80
     usual
    0.80
     described
    0.80
     of
    0.76
     afore
    0.74
     outlined
    0.74
     equivalent
    0.73
     portrayed
    0.72
    Activations Density 0.201%

    No Known Activations