© 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. 8-RES-JB
    11. 10415
    Prev
    Next
    INDEX
    Explanations

    ambiguous or misspelled words

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "ambiguity."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     THR
    -0.74
     numbering
    -0.69
     datas
    -0.66
     pse
    -0.65
    ĸļ
    -0.65
     concent
    -0.61
     compe
    -0.61
     numbered
    -0.61
     snipp
    -0.60
     paralle
    -0.60
    POSITIVE LOGITS
    aughs
    0.86
    uating
    0.84
    zee
    0.81
    aun
    0.80
    uously
    0.80
    andise
    0.79
    oling
    0.78
    agy
    0.78
    ati
    0.77
    agic
    0.76
    Activations Density 0.091%

    No Known Activations