© 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. 8-RES-JB
    11. 17002
    Prev
    Next
    INDEX
    Explanations

    words related to management, employment, and government authority

    oai_token-act-pair · gpt-3.5-turbo

    terms related to authority and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    classic
    -0.70
    rentices
    -0.68
    arter
    -0.66
    td
    -0.66
    anchester
    -0.65
    bm
    -0.64
    Sym
    -0.64
    mx
    -0.63
     Ribbon
    -0.63
    abilia
    -0.62
    POSITIVE LOGITS
     inaction
    1.03
     intervened
    0.94
     intervention
    0.94
     interven
    0.89
     acquies
    0.88
     decides
    0.88
     meddling
    0.85
     disappro
    0.83
     obliged
    0.83
     reacted
    0.82
    Activations Density 0.493%

    No Known Activations