© 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. 9-RES-JB
    11. 17082
    Prev
    Next
    INDEX
    Explanations

    references to wild animals in need of help or care

    oai_token-act-pair · gpt-3.5-turbo

    references to wildlife conservation issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     WRITE
    -0.77
    jri
    -0.75
     PSU
    -0.73
    isSpecialOrderable
    -0.71
     Electronic
    -0.69
     UD
    -0.69
    ourses
    -0.68
     Policies
    -0.66
     Unified
    -0.65
     Coverage
    -0.65
    POSITIVE LOGITS
     extinct
    1.36
     breeding
    1.34
     domest
    1.30
     bred
    1.30
     euth
    1.29
     mating
    1.29
    breeding
    1.20
     hiber
    1.18
     pests
    1.16
     zoo
    1.15
    Activations Density 0.608%

    No Known Activations