© 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. 10-RES-JB
    6. 8157
    Prev
    Next
    INDEX
    Explanations

    verbs related to the action of understanding or learning something new, or phrases indicating a need to keep up with something

    oai_token-act-pair · gpt-3.5-turbo

    variations of the verb "catch."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    die
    -0.72
    INS
    -0.63
    TED
    -0.57
    sburgh
    -0.57
    asonry
    -0.56
    enstein
    -0.56
    ukong
    -0.56
    assisted
    -0.54
     [/
    -0.53
    isable
    -0.53
    POSITIVE LOGITS
     glimps
    1.08
     wind
    1.02
    phrase
    0.97
     glimpse
    0.93
     sight
    0.88
     pneumonia
    0.81
     fire
    0.79
    footed
    0.79
     whiff
    0.78
     up
    0.75
    Activations Density 0.035%

    No Known Activations