© 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. 1-RES-JB
    11. 22699
    Prev
    Next
    INDEX
    Explanations

    the word "rave" and its variations

    oai_token-act-pair · gpt-3.5-turbo

    words related to rave culture and associated activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.67
    ofi
    -0.64
    hops
    -0.63
     optionally
    -0.61
    aceous
    -0.61
    alian
    -0.60
    umin
    -0.60
     appropriation
    -0.59
    apache
    -0.58
    essee
    -0.58
    POSITIVE LOGITS
    rave
    1.01
    lette
    0.90
    rers
    0.83
    OPLE
    0.77
    llers
    0.76
    velt
    0.74
     Disorders
    0.73
    ãĥĥãĤ¯
    0.71
    lly
    0.71
    rer
    0.71
    Activations Density 0.011%

    No Known Activations