© 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. 9117
    Prev
    Next
    INDEX
    Explanations

    details about various animals and species, particularly their colors and physical features

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of various animal species

    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
    Fuel
    -0.72
    Room
    -0.68
    Revolution
    -0.68
     RELE
    -0.67
     Destination
    -0.67
     backstage
    -0.65
    isitions
    -0.64
    Occup
    -0.64
     HQ
    -0.64
    imity
    -0.64
    POSITIVE LOGITS
     deer
    1.46
     squirrel
    1.39
     owl
    1.36
     beetle
    1.35
     monkeys
    1.27
     gorilla
    1.24
     beetles
    1.24
    birds
    1.22
     crab
    1.22
     trout
    1.21
    Activations Density 0.256%

    No Known Activations