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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 232
    Prev
    Next
    INDEX
    Explanations

    names of individuals, possibly from the entertainment industry

    oai_token-act-pair · gpt-3.5-turbo

    names of notable individuals and their affiliations or works

    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
     insignificant
    -0.67
     negligible
    -0.66
    arently
    -0.66
    hap
    -0.65
    notice
    -0.64
    erred
    -0.64
    usually
    -0.64
    idepress
    -0.64
     reasonably
    -0.63
     inconsist
    -0.63
    POSITIVE LOGITS
     joins
    0.96
     Featuring
    0.92
     narr
    0.91
     Guests
    0.87
     showcasing
    0.84
     collaborator
    0.82
     along
    0.82
     aka
    0.82
     alongside
    0.81
     (@
    0.81
    Activations Density 0.471%

    No Known Activations