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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 22687
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical characteristics and behaviors of animals

    oai_token-act-pair · gpt-3.5-turbo

    information related to the size and characteristics of animal species, particularly males and females

    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
    obar
    -0.87
    displayText
    -0.79
    inder
    -0.77
    oman
    -0.77
    channelAvailability
    -0.76
    faith
    -0.75
    ammy
    -0.75
    ersive
    -0.74
    verend
    -0.73
    perial
    -0.73
    POSITIVE LOGITS
     morphology
    1.06
     specimens
    1.05
     glands
    0.98
     species
    0.98
     evolved
    0.98
     habitat
    0.96
     nests
    0.96
     mating
    0.96
     biologists
    0.95
     organisms
    0.95
    Activations Density 0.417%

    No Known Activations