© 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. 9-RES-JB
    11. 8884
    Prev
    Next
    INDEX
    Explanations

    phrases related to change or difference in a situation

    oai_token-act-pair · gpt-3.5-turbo

    references to differing narratives or perspectives in storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sbm
    -0.80
     (>
    -0.78
    anian
    -0.68
     (<
    -0.68
    nor
    -0.67
     drafts
    -0.63
    imar
    -0.62
    ividual
    -0.62
    ricted
    -0.61
    soever
    -0.61
    POSITIVE LOGITS
     trick
    0.97
     kicker
    0.86
     tricks
    0.82
    oops
    0.78
     nutshell
    0.77
     tricky
    0.77
     shenanigans
    0.76
     hitch
    0.74
     ingenious
    0.74
     trouble
    0.72
    Activations Density 1.284%

    No Known Activations