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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 18583
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing explanations or defining concepts

    oai_token-act-pair · gpt-3.5-turbo

    the word "where" in various contexts, indicating locations or settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ³³³³³³³³
    -0.67
    ³³³
    -0.63
    rieve
    -0.63
     Dance
    -0.61
    rolet
    -0.60
     Epidem
    -0.60
     Rite
    -0.58
    ³³³³³³³³³³³³³³³³
    -0.58
     Doctrine
    -0.58
    ME
    -0.58
    POSITIVE LOGITS
    upon
    1.57
    soever
    1.27
    abouts
    1.05
    fore
    1.04
    owler
    0.74
    ever
    0.73
    ipl
    0.73
    ver
    0.72
    anooga
    0.72
    players
    0.71
    Activations Density 0.067%

    No Known Activations