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. 1-RES-JB
    6. 8487
    Prev
    Next
    INDEX
    Explanations

    names and variations related to the name "Human."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of human-related topics or names

    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
    REE
    -0.70
    Hours
    -0.65
     RSS
    -0.65
    Cooldown
    -0.65
    Late
    -0.65
     porous
    -0.63
     gaps
    -0.62
     scant
    -0.61
     longtime
    -0.59
    Temperature
    -0.59
    POSITIVE LOGITS
    ufact
    1.15
    uman
    1.06
    igan
    1.02
    igans
    1.01
    igun
    0.92
    ihilation
    0.92
    ity
    0.88
    vier
    0.88
    itus
    0.85
    iev
    0.85
    Activations Density 0.004%

    No Known Activations