© 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. 21208
    Prev
    Next
    INDEX
    Explanations

    references to actions or events occurring within a process

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to processes or actions occurring 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
    ional
    -0.79
    VILLE
    -0.69
    conom
    -0.69
    afa
    -0.68
    abouts
    -0.67
    LEASE
    -0.66
    uana
    -0.66
    ça
    -0.66
    ARI
    -0.65
    chi
    -0.64
    POSITIVE LOGITS
     guise
    1.50
     midst
    1.38
     wake
    1.24
     name
    1.19
     form
    1.19
     hopes
    1.17
     pursuit
    1.14
     hope
    1.14
     face
    1.11
     aftermath
    1.09
    Activations Density 0.132%

    No Known Activations