© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 2214
    Prev
    Next
    INDEX
    Explanations

    phrases indicating preference or comparison

    oai_token-act-pair · gpt-3.5-turbo

    the comparative term "rather" used to present alternatives or contrasts

    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
    amba
    -0.80
    uay
    -0.75
    ocaust
    -0.74
    ruary
    -0.72
    mberg
    -0.71
    elaide
    -0.71
    clud
    -0.69
    vertising
    -0.69
    eria
    -0.68
    adium
    -0.67
    POSITIVE LOGITS
     unimagin
    0.77
     innocuous
    0.73
     than
    0.71
     unpleasant
    0.70
     inconvenient
    0.68
     amusing
    0.68
     tame
    0.68
     pricey
    0.67
     differentiate
    0.66
     conservative
    0.66
    Activations Density 0.020%

    No Known Activations