© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 6588
    Prev
    Next
    INDEX
    Explanations

    mentions of returns or comebacks

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the return of people or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    conn
    -0.75
    cius
    -0.73
    ghai
    -0.71
    ilateral
    -0.69
    mop
    -0.67
    advant
    -0.67
    opian
    -0.66
    SPONSORED
    -0.66
    romy
    -0.65
    uliffe
    -0.64
    POSITIVE LOGITS
    again
    0.89
     EDITION
    0.85
     triumphant
    0.85
     again
    0.80
     tonight
    0.80
     starring
    0.80
     Featuring
    0.80
     haunt
    0.79
     Season
    0.79
    Season
    0.79
    Activations Density 0.276%

    No Known Activations