Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 14093
    Prev
    Next
    INDEX
    Explanations

    statements or situations that are contradictory

    oai_token-act-pair · gpt-3.5-turbo

    phrases and words related to contradiction or refutation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emetery
    -0.92
    ussed
    -0.79
    sale
    -0.77
    aws
    -0.77
    affer
    -0.76
    anny
    -0.74
    ixties
    -0.73
    ixtape
    -0.73
    Sham
    -0.73
    ARP
    -0.73
    POSITIVE LOGITS
     contradict
    1.11
     contradicted
    0.92
     contradicts
    0.91
     contradictory
    0.87
     substant
    0.86
    ĸļ
    0.83
     contradictions
    0.75
     conflicting
    0.73
     corrobor
    0.72
     precon
    0.70
    Activations Density 0.019%

    No Known Activations