© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 12966
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific person named "Felipe"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "wipe."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    neapolis
    -0.75
    ðĿ
    -0.72
    ãĥĦ
    -0.67
     convol
    -0.65
     sustain
    -0.63
    aken
    -0.62
    achusetts
    -0.62
    orage
    -0.62
     Burlington
    -0.61
    paralleled
    -0.61
    POSITIVE LOGITS
    ipe
    1.32
    iping
    0.90
    gger
    0.86
    phrine
    0.80
    OPLE
    0.77
    hyde
    0.76
    ython
    0.74
    vine
    0.73
    uto
    0.71
    utic
    0.70
    Activations Density 0.010%

    No Known Activations