© 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. 3-RES-JB
    6. 9618
    Prev
    Next
    INDEX
    Explanations

    proper nouns ending in '-inder'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "binder."

    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
    romy
    -0.71
    meric
    -0.71
     tremend
    -0.71
    hovah
    -0.70
    Ĥİ
    -0.70
    eny
    -0.68
    akening
    -0.67
    ramid
    -0.66
    rity
    -0.66
    estic
    -0.66
    POSITIVE LOGITS
    inder
    1.27
     Singh
    0.91
    åĤ
    0.79
    meyer
    0.78
    gaard
    0.78
    holm
    0.77
    Proxy
    0.75
    anguage
    0.73
    ãĥĸ
    0.71
    inders
    0.70
    Activations Density 0.013%

    No Known Activations