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. 813
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases expressing opinions or subjective statements

    oai_token-act-pair · gpt-3.5-turbo

    negative or conditional statements

    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
    ADVERTISEMENT
    -0.63
    mage
    -0.59
    toggle
    -0.57
    acted
    -0.57
     Mage
    -0.57
    gery
    -0.56
    76561
    -0.56
     Dying
    -0.55
     starship
    -0.55
    bryce
    -0.55
    POSITIVE LOGITS
     raining
    0.84
     easier
    0.75
     impossible
    0.69
     uphill
    0.65
    erest
    0.65
    ãĥķãĤ©
    0.64
     dawn
    0.64
     easiest
    0.62
     costs
    0.61
     unclear
    0.61
    Activations Density 1.374%

    No Known Activations