© 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. 10-RES-JB
    11. 7038
    Prev
    Next
    INDEX
    Explanations

    terms related to physical destruction or significant impacts like "ravage" and similar words

    oai_token-act-pair · gpt-3.5-turbo

    references to "ravaged" conditions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onomy
    -0.78
    hyde
    -0.67
    OHN
    -0.66
    terson
    -0.61
     expiration
    -0.60
    ielding
    -0.57
    esis
    -0.57
     Protector
    -0.56
     Consent
    -0.56
    rique
    -0.56
    POSITIVE LOGITS
    itational
    1.03
    atar
    0.98
    estone
    0.95
    estones
    0.94
    idian
    0.92
    esty
    0.87
    itas
    0.85
    ideo
    0.84
    da
    0.83
    aged
    0.82
    Activations Density 0.044%

    No Known Activations