© 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. 6-RES-JB
    11. 7754
    Prev
    Next
    INDEX
    Explanations

    the word "won" with high activation values

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "won't" in various contexts indicating something that is unlikely or impossible to happen

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    illin
    -0.67
    bian
    -0.67
    gypt
    -0.67
     compr
    -0.64
    eki
    -0.64
    OTOS
    -0.61
     cultivating
    -0.61
    dra
    -0.59
     periphery
    -0.58
     constrained
    -0.58
    POSITIVE LOGITS
    't
    1.29
    itive
    1.02
    now
    0.92
    geon
    0.82
    etsk
    0.77
    cest
    0.76
    nings
    0.75
    iors
    0.75
    stall
    0.75
    ims
    0.75
    Activations Density 0.032%

    No Known Activations