Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 580
    Prev
    Next
    INDEX
    Explanations

    words related to negative actions or situations such as theft, hijacking, and destruction

    oai_token-act-pair · gpt-3.5-turbo

    terms related to loss, damage, or capture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ledge
    -0.83
    BIT
    -0.83
    adra
    -0.77
    armed
    -0.74
    adan
    -0.73
    fuck
    -0.72
    cially
    -0.72
    apo
    -0.72
    upuncture
    -0.71
    notice
    -0.70
    POSITIVE LOGITS
     carc
    0.94
     corpses
    0.92
     goods
    0.90
     portions
    0.84
     souls
    0.82
     corpse
    0.79
     manuscripts
    0.76
     portion
    0.76
     assets
    0.74
     copies
    0.72
    Activations Density 0.271%

    No Known Activations