© 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. 11494
    Prev
    Next
    INDEX
    Explanations

    actions or attempts to do something

    oai_token-act-pair · gpt-3.5-turbo

    actions related to attempts or efforts to achieve something

    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
    âĶĢâĶĢâĶĢâĶĢ
    -0.72
     gladly
    -0.69
    shall
    -0.65
     multiplied
    -0.64
     subjected
    -0.62
     littered
    -0.59
     dedicated
    -0.58
     likely
    -0.58
    ç«
    -0.58
     rife
    -0.58
    POSITIVE LOGITS
     somew
    0.84
    balance
    0.79
    ifle
    0.71
     salvage
    0.71
    chet
    0.69
     something
    0.69
     reconcile
    0.66
    omething
    0.64
     himself
    0.63
    ezvous
    0.62
    Activations Density 0.270%

    No Known Activations