© 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. 6-RES-JB
    11. 11941
    Prev
    Next
    INDEX
    Explanations

    comparisons between different options or choices

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating comparison or asking rhetorical questions about choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bis
    -0.70
    KO
    -0.66
    iHUD
    -0.62
    Board
    -0.61
     poppy
    -0.58
     horizont
    -0.57
    Pir
    -0.57
    pi
    -0.57
     carriers
    -0.57
    gra
    -0.57
    POSITIVE LOGITS
    ?!
    1.20
    ?]
    1.12
    ?
    1.09
    ?)
    1.08
    ?),
    1.08
    !?
    1.07
    ?).
    0.99
    ?!"
    0.99
    ?"
    0.98
    ?'
    0.98
    Activations Density 0.159%

    No Known Activations