© 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. 13982
    Prev
    Next
    INDEX
    Explanations

    names of various locations or areas

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'b' 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
    eer
    -0.63
    Magikarp
    -0.59
     suscept
    -0.59
     spect
    -0.58
    e
    -0.57
    TPS
    -0.55
     mole
    -0.55
     Lear
    -0.54
     departure
    -0.54
     Porsche
    -0.54
    POSITIVE LOGITS
    ruary
    1.29
    untu
    1.13
    attery
    1.11
    ureau
    1.11
    rities
    1.10
    rief
    1.10
    abies
    1.09
    odies
    1.07
    esides
    1.07
    rahim
    1.07
    Activations Density 0.064%

    No Known Activations