© 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. 20377
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ever" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ever."

    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
    emia
    -0.77
     antioxid
    -0.67
    icter
    -0.66
    iant
    -0.66
    ESCO
    -0.62
    riad
    -0.62
    arity
    -0.61
     SVG
    -0.60
    Downloadha
    -0.59
    ablo
    -0.59
    POSITIVE LOGITS
    theless
    1.26
    deen
    0.84
     doubted
    0.83
     existed
    0.82
     dreamed
    0.80
    bilt
    0.78
    lasting
    0.76
     heard
    0.75
    THING
    0.75
     entertained
    0.74
    Activations Density 0.029%

    No Known Activations