© 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. 8-RES-JB
    11. 11489
    Prev
    Next
    INDEX
    Explanations

    special characters used as separators or indicators at the end of a section of text

    oai_token-act-pair · gpt-3.5-turbo

    instances of emotional expressions or sentiments

    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
    antine
    -0.70
    mbuds
    -0.67
    cius
    -0.62
     ACS
    -0.61
     Coinbase
    -0.60
    utical
    -0.59
     joints
    -0.59
    izon
    -0.59
    geries
    -0.58
     Modest
    -0.57
    POSITIVE LOGITS
    Narr
    0.82
    Scroll
    0.75
    Course
    0.70
    Shape
    0.70
    Í
    0.69
    elaide
    0.69
    iani
    0.68
    ba
    0.67
    âĹ¼
    0.66
    >>>
    0.66
    Activations Density 0.120%

    No Known Activations