© 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. 0-RES-JB
    11. 1401
    Prev
    Next
    INDEX
    Explanations

    words related to a specific product or brand

    oai_token-act-pair · gpt-3.5-turbo

    specific brand names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mix
    -0.89
    elli
    -0.81
    ainer
    -0.80
    thing
    -0.78
    long
    -0.77
    Neal
    -0.76
    stantial
    -0.75
    mire
    -0.75
    thinking
    -0.74
    ĸļ
    -0.74
    POSITIVE LOGITS
    jriwal
    0.78
    arettes
    0.77
     Beats
    0.74
     Immunity
    0.72
     sclerosis
    0.70
     Emblem
    0.67
    Grade
    0.66
     secondly
    0.64
     parachute
    0.63
     Amph
    0.63
    Activations Density 0.000%

    No Known Activations