© 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. 14039
    Prev
    Next
    INDEX
    Explanations

    phrases indicating impossibility or a strong contrary opinion

    oai_token-act-pair · gpt-3.5-turbo

    negative constructions, particularly related to inability or constraints

    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
    OUS
    -0.72
     Lauder
    -0.71
    phabet
    -0.71
    ously
    -0.66
    rones
    -0.65
    ciating
    -0.65
    tery
    -0.64
     Newspaper
    -0.63
     Need
    -0.61
    column
    -0.60
    POSITIVE LOGITS
     trusted
    1.24
     traced
    1.12
     undone
    1.11
     relied
    1.11
     avoided
    1.08
     construed
    1.07
     blamed
    1.06
     replicated
    1.04
     reconcil
    1.03
     tolerated
    1.03
    Activations Density 0.047%

    No Known Activations