© 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. 17715
    Prev
    Next
    INDEX
    Explanations

    vertical line symbols, particularly those used for formatting in text

    oai_token-act-pair · gpt-3.5-turbo

    structured data or elements related to formatting and organization

    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
    icles
    -0.79
    anium
    -0.75
    itionally
    -0.75
    azon
    -0.73
     Shroud
    -0.73
    imeters
    -0.71
    itives
    -0.70
     Shooting
    -0.69
    owitz
    -0.69
    ory
    -0.68
    POSITIVE LOGITS
    cffffcc
    1.02
    SOURCE
    0.86
    replace
    0.79
    foot
    0.76
    ht
    0.75
    Pg
    0.73
    HEAD
    0.72
    NetMessage
    0.71
    ãĥĩãĤ£
    0.70
    NW
    0.70
    Activations Density 0.035%

    No Known Activations