© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1-RES-JB
    11. 2288
    Prev
    Next
    INDEX
    Explanations

    instances of the word "countless" followed by descriptions of quantity or actions

    oai_token-act-pair · gpt-3.5-turbo

    the word "countless" to emphasize a large, indeterminate number of items or occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adish
    -0.77
    aca
    -0.75
    enders
    -0.75
    ema
    -0.73
    amina
    -0.72
    atem
    -0.69
    pose
    -0.68
    ENA
    -0.68
    _-
    -0.67
    afort
    -0.66
    POSITIVE LOGITS
     countless
    0.95
    ãĤ£
    0.90
     thousands
    0.89
    ãĤ§
    0.85
    ãĤ©
    0.85
    ãĥ¼ãĥĨãĤ£
    0.84
     millions
    0.83
     billions
    0.80
     innumerable
    0.77
    ãĥ¼ãĥĨ
    0.76
    Activations Density 0.010%

    No Known Activations