© 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. 1-RES-JB
    11. 16435
    Prev
    Next
    INDEX
    Explanations

    instances where something is being controlled or influenced by an authoritative force

    oai_token-act-pair · gpt-3.5-turbo

    words related to control or authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    swick
    -0.75
    este
    -0.72
    Tok
    -0.71
    att
    -0.69
    Hat
    -0.69
     Dak
    -0.69
     Charity
    -0.69
    Mary
    -0.67
     Fighting
    -0.67
     Horn
    -0.66
    POSITIVE LOGITS
     dictated
    1.48
     dictate
    1.35
     dictates
    1.26
     confir
    1.12
     dict
    0.93
     rul
    0.83
     governs
    0.83
     lapt
    0.81
     corrid
    0.81
    é¾įå¥ij士
    0.79
    Activations Density 0.013%

    No Known Activations