© 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. 1-RES-JB
    11. 3961
    Prev
    Next
    INDEX
    Explanations

    words related to conflicting or contradictory information

    oai_token-act-pair · gpt-3.5-turbo

    references to conflicting information or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chens
    -0.81
    abit
    -0.79
    rix
    -0.76
    aday
    -0.76
    fm
    -0.75
    ney
    -0.74
    frey
    -0.74
    bern
    -0.73
    rection
    -0.73
    adr
    -0.73
    POSITIVE LOGITS
     conflicting
    1.57
     contradictory
    1.30
     undermin
    0.99
     discrep
    0.97
     conflicted
    0.93
     conflicts
    0.89
     sexes
    0.88
     guiActiveUn
    0.85
     predic
    0.84
     opinions
    0.83
    Activations Density 0.010%

    No Known Activations