© 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. 11846
    Prev
    Next
    INDEX
    Explanations

    instances of the word "almost" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing the concept of "almost" or "virtually" in relation to quantities or situations

    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
    agate
    -0.84
    oran
    -0.68
    oris
    -0.66
     messenger
    -0.63
    olor
    -0.61
     RTX
    -0.60
    ":[
    -0.60
     Females
    -0.59
     Awakening
    -0.58
    ilic
    -0.58
    POSITIVE LOGITS
     identical
    0.85
     limitless
    0.82
    zero
    0.79
     exclusively
    0.79
    thood
    0.78
     unbearable
    0.70
    900
    0.69
    empty
    0.69
     ident
    0.67
    everything
    0.66
    Activations Density 0.055%

    No Known Activations