© 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. 7-RES-JB
    11. 3027
    Prev
    Next
    INDEX
    Explanations

    comparisons or contrasts

    oai_token-act-pair · gpt-3.5-turbo

    the word "even" when it is used to emphasize a surprising or unexpected situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rend
    -0.91
    HCR
    -0.74
    reating
    -0.72
    ync
    -0.72
    idon
    -0.71
    ugal
    -0.71
    othy
    -0.70
    chn
    -0.69
    aim
    -0.67
    ected
    -0.66
    POSITIVE LOGITS
     remotely
    1.01
    handed
    1.00
     though
    0.89
    handedly
    0.85
     tho
    0.79
     numbered
    0.77
    este
    0.67
    ITY
    0.64
     marginally
    0.64
     moderately
    0.63
    Activations Density 0.063%

    No Known Activations