© 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 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. 8-RES-JB
    11. 1055
    Prev
    Next
    INDEX
    Explanations

    questions or statements ending with the word "do."

    oai_token-act-pair · gpt-3.5-turbo

    questions beginning with "do."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.81
    workshop
    -0.79
    boarding
    -0.77
    cream
    -0.69
    isu
    -0.67
    ieu
    -0.67
    ruption
    -0.67
    ItemTracker
    -0.66
    dom
    -0.64
    iltration
    -0.64
    POSITIVE LOGITS
    omsday
    0.98
    zens
    0.87
     impressions
    0.84
    herty
    0.80
    ctors
    0.79
     things
    0.79
    ctr
    0.73
     preced
    0.70
    ppel
    0.69
     exist
    0.68
    Activations Density 0.045%

    No Known Activations