© 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. 11-RES-JB
    11. 17675
    Prev
    Next
    INDEX
    Explanations

    words related to discussions, viewpoints, and free expression

    oai_token-act-pair · gpt-3.5-turbo

    elements of open dialogue and the importance of diverse opinions in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Miracle
    -0.81
    ©¶æ¥µ
    -0.75
    aunder
    -0.71
    mallow
    -0.71
    stasy
    -0.71
    alloween
    -0.70
     Pwr
    -0.70
     Hyde
    -0.70
     Glow
    -0.69
    soDeliveryDate
    -0.69
    POSITIVE LOGITS
     dissenting
    1.71
     disagreement
    1.65
     opinions
    1.61
     viewpoints
    1.57
     dissent
    1.57
     disagreements
    1.56
     debate
    1.51
     reasoned
    1.47
     disagree
    1.43
     opinion
    1.40
    Activations Density 0.614%

    No Known Activations