© 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. 4996
    Prev
    Next
    INDEX
    Explanations

    references to various types of knowledge

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to knowledge and awareness about various subjects

    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
    ratulations
    -0.94
    earchers
    -0.91
    enaries
    -0.74
    appointed
    -0.73
    aunder
    -0.72
    iscovery
    -0.71
    Explore
    -0.70
    orthy
    -0.69
    ciation
    -0.69
    brother
    -0.68
    POSITIVE LOGITS
     geography
    0.95
     economics
    0.92
     facts
    0.90
     how
    0.90
     nuances
    0.89
     history
    0.85
     physics
    0.85
     anatomy
    0.84
     languages
    0.82
     mathematics
    0.81
    Activations Density 0.209%

    No Known Activations