© 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. 7-RES-JB
    11. 18756
    Prev
    Next
    INDEX
    Explanations

    terms related to resistance, especially in the context of biology or physical attributes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of resistance, particularly in the context of medical or social challenges

    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
    ghazi
    -0.87
    =-=-=-=-
    -0.80
    osta
    -0.75
     Lumpur
    -0.73
    ewater
    -0.70
    lehem
    -0.67
    inas
    -0.65
    oba
    -0.65
    zos
    -0.65
    tan
    -0.65
    POSITIVE LOGITS
     resistance
    0.78
     thereto
    0.78
     suscept
    0.76
     fighters
    0.75
     resistant
    0.75
     inhibitor
    0.74
     tiss
    0.72
    istance
    0.72
    ENCE
    0.72
     aggressively
    0.70
    Activations Density 0.032%

    No Known Activations