© 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. 11-RES-JB
    11. 22108
    Prev
    Next
    INDEX
    Explanations

    phrases related to the reduction or decrease of various factors or elements, such as costs, risks, numbers, demands, time, or opportunities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the" and phrases indicating reduction or increase in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gat
    -0.72
    perse
    -0.69
    mire
    -0.68
    zag
    -0.67
    aday
    -0.67
    gom
    -0.67
    çīĪ
    -0.66
    outhern
    -0.65
    pered
    -0.65
    ouse
    -0.64
    POSITIVE LOGITS
     likelihood
    1.61
     amount
    1.55
     chances
    1.46
     number
    1.43
     probability
    1.38
     effectiveness
    1.35
     odds
    1.31
     incidence
    1.25
     size
    1.24
     frequency
    1.23
    Activations Density 0.122%

    No Known Activations