© 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. 4-RES-JB
    11. 7290
    Prev
    Next
    INDEX
    Explanations

    The neuron primarily looks for phrases mentioning comparisons using the phrase "at least."

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a minimum or a comparative sentiment

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

    No Comments

    Negative Logits
    bj
    -0.68
    rend
    -0.66
    rence
    -0.63
    hr
    -0.63
    taboola
    -0.62
    kefeller
    -0.62
    dal
    -0.61
    ses
    -0.60
    shr
    -0.59
    iph
    -0.59
    POSITIVE LOGITS
    uner
    0.75
     partly
    0.73
     toler
    0.72
    fair
    0.68
     squares
    0.67
     partially
    0.65
    een
    0.65
     judging
    0.64
     theoretically
    0.62
    Station
    0.61
    Activations Density 0.021%

    No Known Activations