© 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. 3-RES-JB
    11. 23444
    Prev
    Next
    INDEX
    Explanations

    HTML tags and comments

    oai_token-act-pair · gpt-3.5-turbo

    HTML comments and markup elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ividual
    -0.43
    ãĥ¼ãĥĨãĤ£
    -0.40
    uese
    -0.38
    ulous
    -0.37
    dfx
    -0.35
    itialized
    -0.35
     CLSID
    -0.34
    gins
    -0.34
    abee
    -0.34
    eligible
    -0.33
    POSITIVE LOGITS
    terness
    0.40
     âĢº
    0.37
    WAYS
    0.35
     WATCHED
    0.35
    natureconservancy
    0.35
    RESULTS
    0.34
    taboola
    0.34
     REUTERS
    0.34
    APD
    0.34
     CNBC
    0.33
    Activations Density 2.754%

    No Known Activations