© 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. 16738
    Prev
    Next
    INDEX
    Explanations

    names or terms with the string "ang" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to specific types of animals

    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
    cloth
    -0.72
     compensated
    -0.68
     oats
    -0.67
    SOURCE
    -0.67
    cki
    -0.65
     captcha
    -0.63
     Horowitz
    -0.63
    Ö¼
    -0.61
    phia
    -0.60
    pring
    -0.59
    POSITIVE LOGITS
    aroo
    1.39
    omez
    1.17
    lasses
    1.09
    raph
    1.06
    regate
    1.04
    etsu
    1.01
    arin
    1.00
    iov
    0.99
    lia
    0.99
    entle
    0.97
    Activations Density 0.047%

    No Known Activations