© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 12581
    Prev
    Next
    INDEX
    Explanations

    words related to persuasion or influence, focusing on terms like "preaches," "submit," "persuade," and "convince."

    oai_token-act-pair · gpt-3.5-turbo

    words related to themes of oppression and control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spoilers
    -0.64
     GOODMAN
    -0.62
     wording
    -0.58
    Bench
    -0.56
     variants
    -0.55
     booking
    -0.55
     rollout
    -0.55
     Isles
    -0.54
     bookstore
    -0.54
    DOWN
    -0.53
    POSITIVE LOGITS
    rehend
    0.89
    ersed
    0.85
    posed
    0.83
    etically
    0.80
    ented
    0.80
    pires
    0.78
    overe
    0.78
    ceive
    0.76
    formed
    0.76
    ceed
    0.76
    Activations Density 0.150%

    No Known Activations