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. 6-RES-JB
    6. 8111
    Prev
    Next
    INDEX
    Explanations

    phrases or expressions indicating a contrast or contradiction

    oai_token-act-pair · gpt-3.5-turbo

    phrases that contrast common beliefs or expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    estones
    -0.81
    ross
    -0.77
    ahead
    -0.75
    acht
    -0.70
    morning
    -0.69
    reau
    -0.69
    onna
    -0.68
    uben
    -0.67
    ocamp
    -0.67
    illed
    -0.66
    POSITIVE LOGITS
     precon
    0.96
     stereotypes
    0.94
     expectations
    0.90
     stereotypical
    0.88
     stereotype
    0.84
     prevailing
    0.80
     perceptions
    0.77
     belief
    0.74
     conventional
    0.73
     conceptions
    0.68
    Activations Density 0.227%

    No Known Activations