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

    Neuronpedia

    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. 11-RES-JB
    11. 22333
    Prev
    Next
    INDEX
    Explanations

    references to different species

    oai_token-act-pair · gpt-3.5-turbo

    mentions of different species and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pees
    -0.82
    dan
    -0.81
    ibur
    -0.76
    aiden
    -0.73
    zes
    -0.71
    pton
    -0.70
    ouk
    -0.69
    zers
    -0.68
    Machine
    -0.67
    endar
    -0.66
    POSITIVE LOGITS
     richness
    1.28
     species
    1.09
     inhab
    1.03
    inctions
    1.02
     extinct
    1.01
     Homo
    0.99
    species
    0.98
     extinction
    0.98
     biologists
    0.96
     Species
    0.94
    Activations Density 0.068%

    No Known Activations