© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 23928
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparing products or devices in terms of price and competition

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating possession or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Runner
    -0.77
    âĺħâĺħ
    -0.75
    Discuss
    -0.74
    YING
    -0.69
    DEP
    -0.69
    eele
    -0.68
    istani
    -0.67
    enf
    -0.66
    âĢ¢âĢ¢
    -0.65
    Uncommon
    -0.64
    POSITIVE LOGITS
     kicks
    0.73
    bol
    0.69
    upuncture
    0.68
    sav
    0.63
     chambers
    0.62
    anth
    0.62
     cured
    0.61
    utical
    0.60
     channels
    0.60
     cush
    0.60
    Activations Density 0.000%

    No Known Activations