© 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. 2-RES-JB
    11. 17422
    Prev
    Next
    INDEX
    Explanations

    numbers associated with rarity or frequency

    oai_token-act-pair · gpt-3.5-turbo

    intensifying adverbs that emphasize a degree of quality or state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osal
    -0.73
     phyl
    -0.72
    arians
    -0.68
    åĤ
    -0.68
    æ©
    -0.67
    ierre
    -0.67
     gent
    -0.66
     coh
    -0.64
    çĦ
    -0.63
    à
    -0.62
    POSITIVE LOGITS
     Again
    0.89
     Helpful
    0.88
     Enough
    0.85
     Rating
    0.84
     Likely
    0.84
     Hits
    0.83
     Leader
    0.83
     Funny
    0.82
     Advice
    0.82
     Fine
    0.81
    Activations Density 0.029%

    No Known Activations