© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 14671
    Prev
    Next
    INDEX
    Explanations

    suggestions or possibilities for actions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    phrases proposing actions or suggestions, often starting with "why not."

    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
    digit
    -0.65
    photo
    -0.65
    ixel
    -0.64
    operated
    -0.63
     Alleg
    -0.63
    wordpress
    -0.63
    ItemTracker
    -0.63
    chat
    -0.62
    vor
    -0.62
    iHUD
    -0.61
    POSITIVE LOGITS
    ?]
    0.84
     invoke
    0.76
    ]).
    0.75
    itia
    0.75
     emulate
    0.73
    ucc
    0.72
     concede
    0.71
     succumb
    0.70
     unleash
    0.69
     intervene
    0.68
    Activations Density 0.037%

    No Known Activations