© 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. 2-RES-JB
    11. 17651
    Prev
    Next
    INDEX
    Explanations

    mentions or discussions related to estimates, specifically involving numbers or values

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "estimate."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ModLoader
    -0.74
    spr
    -0.70
    acco
    -0.69
     disg
    -0.69
    perty
    -0.69
    udeb
    -0.68
    inis
    -0.67
     challeng
    -0.67
     sidel
    -0.67
    eatures
    -0.65
    POSITIVE LOGITS
    imate
    1.03
    uated
    0.86
    itarian
    0.85
    mental
    0.82
    oice
    0.80
    uate
    0.74
    andum
    0.74
    imates
    0.73
    lda
    0.72
    vation
    0.72
    Activations Density 0.020%

    No Known Activations