© 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. 2-RES-JB
    11. 17062
    Prev
    Next
    INDEX
    Explanations

    words related to contradictions

    oai_token-act-pair · gpt-3.5-turbo

    references to contradictions and inconsistencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    undai
    -0.88
    otin
    -0.87
    rol
    -0.85
    obbies
    -0.83
    odes
    -0.81
    asted
    -0.79
    gone
    -0.78
    thel
    -0.75
    iatric
    -0.75
    aldi
    -0.74
    POSITIVE LOGITS
     contradiction
    1.04
    xual
    1.03
    hift
    0.81
     paradox
    0.80
     contradictory
    0.79
     inconsistency
    0.77
    naire
    0.76
     contradictions
    0.75
     juxtap
    0.75
     contradict
    0.73
    Activations Density 0.011%

    No Known Activations