© 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. 20012
    Prev
    Next
    INDEX
    Explanations

    phrases indicating responsibility or authority

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to authority and leadership roles

    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
    Boo
    -0.71
    anus
    -0.66
    chrom
    -0.62
    æĺ
    -0.61
    enegger
    -0.61
    mpeg
    -0.60
     testament
    -0.60
    aren
    -0.59
    ITCH
    -0.59
    retch
    -0.59
    POSITIVE LOGITS
    hyde
    0.89
     overseeing
    0.88
    boards
    0.82
    llan
    0.73
    manship
    0.72
    cules
    0.66
    heet
    0.66
    posts
    0.64
    taker
    0.64
     of
    0.64
    Activations Density 0.020%

    No Known Activations