© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 3755
    Prev
    Next
    INDEX
    Explanations

    dates expressed in a numerical format

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating belief or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    liest
    -0.58
    lihood
    -0.57
    BILITY
    -0.48
    kson
    -0.47
    iculty
    -0.47
    erness
    -0.46
    alties
    -0.45
    herty
    -0.44
    BILITIES
    -0.43
    stood
    -0.43
    POSITIVE LOGITS
     thous
    0.49
     py
    0.42
     pione
    0.41
    Interstitial
    0.41
    oreAnd
    0.40
     eleph
    0.38
    Ü
    0.38
     fuckin
    0.38
    POST
    0.37
    ¼
    0.37
    Activations Density 1.102%

    No Known Activations