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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 20872
    Prev
    Next
    INDEX
    Explanations

    phrases related to controversial or debated topics

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word “the” and its variations in context, indicating a focus on specifics or details 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
    gon
    -0.84
    duino
    -0.77
    tackle
    -0.77
    cil
    -0.72
    eat
    -0.71
    cair
    -0.69
    ce
    -0.68
    aternity
    -0.68
    elaide
    -0.68
    Serv
    -0.68
    POSITIVE LOGITS
     facts
    1.35
    ories
    1.25
     evidence
    1.23
     testimonies
    1.20
     conclusions
    1.18
     truth
    1.18
     Facts
    1.13
     findings
    1.12
     assertions
    1.12
     slightest
    1.12
    Activations Density 0.338%

    No Known Activations