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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2782
    Prev
    Next
    INDEX
    Explanations

    numerical ranges or quantities mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to ranges and numerical values

    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
     Voices
    -0.74
    043
    -0.64
     Duo
    -0.62
     457
    -0.61
     Donovan
    -0.61
     Gutenberg
    -0.61
     Ki
    -0.61
     Garner
    -0.60
     Pryor
    -0.60
    yss
    -0.60
    POSITIVE LOGITS
    isma
    0.72
    ¶
    0.70
    cffff
    0.68
    10
    0.68
    8
    0.67
    iron
    0.66
    8000
    0.65
    dam
    0.65
    adden
    0.65
    ocene
    0.63
    Activations Density 0.078%

    No Known Activations