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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 18953
    Prev
    Next
    INDEX
    Explanations

    phrases related to quantity or scale

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "many" and its variations, often in contexts discussing abundance or frequency

    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
     mobility
    -0.59
    ··
    -0.56
     eligibility
    -0.56
    Delivery
    -0.56
     curve
    -0.56
     mats
    -0.55
     treadmill
    -0.55
    AMA
    -0.55
    Abstract
    -0.54
     tempo
    -0.54
    POSITIVE LOGITS
    many
    1.11
    dozen
    1.03
     many
    0.98
    undreds
    0.96
    perhaps
    0.92
    ousands
    0.90
     thousands
    0.87
    including
    0.83
    illion
    0.83
    ilo
    0.83
    Activations Density 0.097%

    No Known Activations