© 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. 17092
    Prev
    Next
    INDEX
    Explanations

    mentions of challenging or unstable situations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to varying conditions or situations

    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
    amiya
    -0.68
    mson
    -0.64
    actory
    -0.64
    cot
    -0.64
    ignt
    -0.63
    oval
    -0.61
    vard
    -0.60
    urdue
    -0.59
    olulu
    -0.58
    nant
    -0.56
    POSITIVE LOGITS
     varies
    0.93
     changed
    0.82
     differs
    0.79
     differed
    0.75
     vary
    0.74
     varied
    0.72
     deteriorated
    0.72
     fluct
    0.70
     understandably
    0.67
     outlook
    0.66
    Activations Density 0.574%

    No Known Activations