© 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. 3622
    Prev
    Next
    INDEX
    Explanations

    email-related actions such as "Close"

    oai_token-act-pair · gpt-3.5-turbo

    references to votes or voting processes

    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
    thumbnails
    -0.84
    Catal
    -0.84
    女
    -0.83
    MAT
    -0.73
    Struct
    -0.73
    Translation
    -0.73
    Gene
    -0.70
    Sa
    -0.67
    Attempt
    -0.67
    Vari
    -0.65
    POSITIVE LOGITS
    resy
    0.80
     Trooper
    0.70
    angering
    0.65
    rophe
    0.63
    itars
    0.63
     retaliation
    0.62
    akening
    0.61
    rupt
    0.61
    licks
    0.60
    hitting
    0.60
    Activations Density 0.000%

    No Known Activations