© 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. 0-RES-JB
    11. 10284
    Prev
    Next
    INDEX
    Explanations

    numeric values embedded in gibberish text

    oai_token-act-pair · gpt-3.5-turbo

    specific special characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    --------------------------------------------------------
    -0.67
    --------------------------------
    -0.67
     Thur
    -0.65
    ................................................................
    -0.65
    (-
    -0.63
    tein
    -0.62
    hor
    -0.62
     pupils
    -0.61
    ieri
    -0.61
    REM
    -0.60
    POSITIVE LOGITS
    ãĥĸ
    0.98
    é¾įå
    0.70
    76561
    0.69
    ãĥ¬
    0.68
    rencies
    0.67
    ometimes
    0.66
     thrott
    0.65
     UID
    0.65
    abwe
    0.65
    apego
    0.63
    Activations Density 0.000%

    No Known Activations