© 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. 11-RES-JB
    11. 3461
    Prev
    Next
    INDEX
    Explanations

    phrases describing specific attributes or features

    oai_token-act-pair · gpt-3.5-turbo

    quantities and measurements related to objects and their properties

    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
    projects
    -0.89
    OWS
    -0.77
    Train
    -0.76
    onse
    -0.76
    sports
    -0.75
    cakes
    -0.75
    bis
    -0.75
    Products
    -0.71
    Music
    -0.71
    arten
    -0.70
    POSITIVE LOGITS
     tendency
    1.25
     lifespan
    1.19
     diameter
    1.09
     expiration
    1.07
     drawback
    1.04
     propensity
    1.02
     resemblance
    1.02
     radius
    0.97
     capacity
    0.96
     reputation
    0.95
    Activations Density 0.207%

    No Known Activations