© 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. 9-RES-JB
    11. 18103
    Prev
    Next
    INDEX
    Explanations

    names and terms related to "Mendez" or "Mendoza"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Mend" and its variations, likely capturing mentions of specific names or entities related to "MIT."

    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
    wark
    -0.96
    blade
    -0.77
    naire
    -0.69
    bones
    -0.64
     Antar
    -0.64
    draw
    -0.62
    tones
    -0.61
    ngth
    -0.60
    holder
    -0.59
    ãģĦ
    -0.59
    POSITIVE LOGITS
    chell
    1.13
    igated
    0.93
    ochond
    0.91
    igation
    0.82
    edly
    0.81
    igious
    0.79
    igating
    0.78
    igate
    0.78
     Mayhem
    0.75
    chel
    0.75
    Activations Density 0.056%

    No Known Activations