© 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. 7679
    Prev
    Next
    INDEX
    Explanations

    references to bodies of water such as rivers, lakes, or seas

    oai_token-act-pair · gpt-3.5-turbo

    terms related to individuals or entities that engage in certain activities or practices

    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
     confidence
    -0.76
     reflex
    -0.67
     fusion
    -0.63
     TI
    -0.61
     borrow
    -0.61
     prod
    -0.60
     elastic
    -0.60
     relief
    -0.60
     commend
    -0.59
     borrowed
    -0.59
    POSITIVE LOGITS
    aters
    4.74
    ater
    3.06
    atre
    1.85
    ATER
    1.64
    ating
    1.44
    ATING
    1.38
    ators
    1.37
    ates
    1.31
    ats
    1.27
    ATES
    1.24
    Activations Density 0.008%

    No Known Activations