© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RES-JB
    11. 3823
    Prev
    Next
    INDEX
    Explanations

    mentions of slugs or snails in physical or metaphorical contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to slugs and related entities

    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
    mental
    -0.73
    foreseen
    -0.70
    lesiastical
    -0.68
    Production
    -0.68
     srfAttach
    -0.66
     Scotia
    -0.65
    SPONSORED
    -0.65
    raising
    -0.64
     Citizens
    -0.62
    annis
    -0.62
    POSITIVE LOGITS
     slug
    1.18
     Slug
    1.07
    gers
    1.02
    ging
    0.98
    bats
    0.94
    gery
    0.90
    ged
    0.89
    ger
    0.88
    bowl
    0.83
    atoon
    0.81
    Activations Density 0.007%

    No Known Activations