© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 14935
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussions or statements on specific topics

    oai_token-act-pair · gpt-3.5-turbo

    references to topics or subjects being discussed

    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
    aurus
    -0.67
    ngth
    -0.66
    âĢł
    -0.64
    let
    -0.63
    fighters
    -0.63
    ãĥīãĥ©
    -0.63
    Layer
    -0.62
    AppData
    -0.62
    pps
    -0.61
    *,
    -0.61
    POSITIVE LOGITS
     behalf
    1.26
     basis
    1.24
     topic
    1.20
     eve
    1.16
     grounds
    1.10
     merits
    1.08
     occasion
    1.05
     heels
    1.02
     sidelines
    1.00
     subject
    0.98
    Activations Density 0.154%

    No Known Activations