© 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. 1554
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names in a text

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'T' in various contexts

    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
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.68
     tem
    -0.67
    lihood
    -0.66
     descending
    -0.65
     precedent
    -0.65
     lear
    -0.63
     warr
    -0.63
     woo
    -0.63
     indu
    -0.62
     ascending
    -0.62
    POSITIVE LOGITS
    erence
    1.33
    anya
    1.26
    ania
    1.21
    essa
    1.20
    oni
    1.20
    ribute
    1.18
    omm
    1.18
    ributes
    1.17
    ONY
    1.17
    amera
    1.17
    Activations Density 0.038%

    No Known Activations