© 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. 11237
    Prev
    Next
    INDEX
    Explanations

    phrases related to placement or positioning

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with placing or positioning objects

    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
    ucci
    -0.76
    esome
    -0.69
    SB
    -0.69
    issance
    -0.67
    straight
    -0.62
    dy
    -0.61
    LS
    -0.61
    hoe
    -0.60
    tub
    -0.60
    uary
    -0.59
    POSITIVE LOGITS
     bets
    1.42
     emphasis
    1.12
     blame
    1.11
    holders
    0.93
    holder
    0.90
     cursor
    0.87
     electrodes
    0.85
     reliance
    0.81
     bet
    0.79
     moratorium
    0.77
    Activations Density 0.089%

    No Known Activations