© 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. 12079
    Prev
    Next
    INDEX
    Explanations

    instances of the word "be" followed by other words

    oai_token-act-pair · gpt-3.5-turbo

    statements about potential or hypothetical 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
     tends
    -0.63
     consumes
    -0.62
     seldom
    -0.62
    airy
    -0.61
    plex
    -0.60
    often
    -0.60
     appears
    -0.59
    ele
    -0.59
     Kub
    -0.58
    verend
    -0.57
    POSITIVE LOGITS
    ħĭ
    0.98
     feas
    0.83
     mistaken
    0.76
     conce
    0.75
     someday
    0.74
    ivably
    0.72
    ADRA
    0.72
    efe
    0.70
    oÄŁ
    0.69
     DACA
    0.68
    Activations Density 0.150%

    No Known Activations