© 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. 12-RES-JB
    11. 3889
    Prev
    Next
    INDEX
    Explanations

    singular indefinite articles followed by adjectives

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    various forms of "a" to emphasize the significance or quality of a noun

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    ean
    -0.83
    chairs
    -0.82
    anism
    -0.82
    agents
    -0.81
    anders
    -0.81
    friends
    -0.80
    eyes
    -0.79
    ares
    -0.79
    mares
    -0.76
    devices
    -0.76
    POSITIVE LOGITS
     possibility
    1.19
     misconception
    1.17
     difference
    1.16
     temptation
    1.16
     reason
    1.13
     tendency
    1.10
     shortage
    1.10
     danger
    1.08
     chance
    1.08
     discrepancy
    1.06
    Activations Density 0.170%

    No Known Activations