© 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. 7-RES-JB
    11. 23796
    Prev
    Next
    INDEX
    Explanations

    phrases where something is categorized or labeled as something specific

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "as" followed by different descriptors or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reiterate
    -0.68
    Length
    -0.68
    raq
    -0.66
    imize
    -0.66
    atl
    -0.63
    itiveness
    -0.63
    awar
    -0.62
    auldron
    -0.62
    width
    -0.62
    scenes
    -0.62
    POSITIVE LOGITS
     belonging
    0.95
     follows
    0.92
    pers
    0.81
    criptions
    0.76
     opposed
    0.76
    pires
    0.75
     conscientious
    0.74
    pired
    0.74
     having
    0.72
     well
    0.71
    Activations Density 0.112%

    No Known Activations