© 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. 11-RES-JB
    11. 17615
    Prev
    Next
    INDEX
    Explanations

    mentions of quantities, particularly large numbers or counts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating quantities or counts related to large numbers

    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
     breeze
    -0.59
     jaws
    -0.59
    ffen
    -0.58
     pose
    -0.56
     poses
    -0.55
     spont
    -0.53
     sten
    -0.53
     disclaim
    -0.53
     condem
    -0.52
     passers
    -0.52
    POSITIVE LOGITS
    capacity
    1.22
    drive
    1.13
    tones
    1.13
    population
    1.12
    whelming
    1.12
     9000
    1.07
     4000
    1.04
    worked
    1.04
    priced
    1.02
     200
    1.01
    Activations Density 0.043%

    No Known Activations