© 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. 11-RES-JB
    11. 22450
    Prev
    Next
    INDEX
    Explanations

    phrases related to denial or refutation

    oai_token-act-pair · gpt-3.5-turbo

    references to denials or claims made by individuals or entities

    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
    æĹ
    -0.78
    hei
    -0.76
     wisely
    -0.76
    Visual
    -0.75
    udder
    -0.73
    must
    -0.72
    eps
    -0.72
    acent
    -0.71
    iour
    -0.71
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.70
    POSITIVE LOGITS
     allegation
    1.76
     allegations
    1.59
     accusation
    1.52
     accusations
    1.39
     complaint
    1.23
     investigation
    1.20
     authenticity
    1.17
     discrepancy
    1.17
     dossier
    1.16
     incident
    1.16
    Activations Density 0.288%

    No Known Activations