© 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. 23641
    Prev
    Next
    INDEX
    Explanations

    mentions of different types of apes, particularly gorillas

    oai_token-act-pair · gpt-3.5-turbo

    references to different species of apes and primates

    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
    gren
    -0.88
    WIND
    -0.76
    QL
    -0.75
    turn
    -0.73
    spring
    -0.73
    Nap
    -0.72
    s
    -0.72
    sol
    -0.70
    inen
    -0.69
    ÑĮ
    -0.67
    POSITIVE LOGITS
     apes
    1.19
     chimpanzees
    1.13
     gorilla
    1.08
     Haram
    1.07
     primates
    1.03
     chimpan
    0.94
    zee
    0.93
     monkeys
    0.89
    zees
    0.89
     saf
    0.88
    Activations Density 0.024%

    No Known Activations