© 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. 12-RES-JB
    11. 3900
    Prev
    Next
    INDEX
    Explanations

    information about technology updates and events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    repeated mentions of the word "this" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    ocity
    -0.76
    cks
    -0.75
    aviour
    -0.70
    velt
    -0.70
    andowski
    -0.70
    _>
    -0.68
    gans
    -0.68
    OTOS
    -0.67
    izontal
    -0.67
    atography
    -0.67
    POSITIVE LOGITS
     weekend
    1.41
     coming
    1.32
     fall
    1.32
     autumn
    1.26
     summer
    1.26
     upcoming
    1.25
     week
    1.22
     month
    1.22
     Fall
    1.20
     Saturday
    1.17
    Activations Density 0.079%

    No Known Activations