© 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. 3535
    Prev
    Next
    INDEX
    Explanations

    terms related to potential choices or substitutes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of alternatives in various contexts

    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
    awar
    -0.88
    ric
    -0.80
    gran
    -0.72
     Saud
    -0.71
    haw
    -0.71
    Que
    -0.70
    cer
    -0.70
    bra
    -0.70
    Charge
    -0.69
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.68
    POSITIVE LOGITS
     alternatives
    1.51
     alternative
    1.16
    ensical
    1.01
     options
    0.95
    é¾įå¥ij士
    0.95
    atives
    0.93
     replacements
    0.90
     Altern
    0.88
     solutions
    0.88
    itutes
    0.87
    Activations Density 0.005%

    No Known Activations