© 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. 2-RES-JB
    11. 23681
    Prev
    Next
    INDEX
    Explanations

    references to specific animals

    oai_token-act-pair · gpt-3.5-turbo

    names of various animal species, particularly reptiles and marine creatures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    APD
    -0.68
    ãĥ´ãĤ¡
    -0.66
    ASED
    -0.66
     KH
    -0.64
     tert
    -0.64
    Interstitial
    -0.63
    MED
    -0.62
     instantaneous
    -0.62
    OVER
    -0.62
    fficiency
    -0.61
    POSITIVE LOGITS
    fish
    1.12
     beetle
    1.04
    flies
    0.96
    minecraft
    0.92
     pup
    0.87
     crabs
    0.85
    eers
    0.85
     beetles
    0.83
     crab
    0.80
     mascot
    0.80
    Activations Density 0.238%

    No Known Activations