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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1421
    Prev
    Next
    INDEX
    Explanations

    locations and names related to conflict zones

    oai_token-act-pair · gpt-3.5-turbo

    names and references to specific individuals and locations involved in conflicts

    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
     roller
    -0.79
    itialized
    -0.76
     coaster
    -0.76
     Phillies
    -0.75
     locom
    -0.75
     Victorian
    -0.73
    erella
    -0.73
     pitchers
    -0.73
     mammal
    -0.73
     Wolverine
    -0.71
    POSITIVE LOGITS
    qa
    1.23
    qqa
    1.16
    aq
    1.16
     Hassan
    1.15
    awi
    1.15
    azi
    1.15
     Kaf
    1.12
     Gaddafi
    1.10
     Hasan
    1.09
    iyah
    1.08
    Activations Density 0.247%

    No Known Activations