© 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. 5941
    Prev
    Next
    INDEX
    Explanations

    accidents or incidents involving collisions or impacts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the article "a" used in various contexts

    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
    OTOS
    -0.77
    rils
    -0.76
    Hour
    -0.75
    attacks
    -0.72
    isodes
    -0.72
    Ultimate
    -0.71
    Interview
    -0.70
    Weapons
    -0.70
     Cases
    -0.69
    Reviewer
    -0.69
    POSITIVE LOGITS
     parked
    1.01
     cliff
    0.99
     nearby
    0.96
     mailbox
    0.93
     crowded
    0.93
     ditch
    0.92
     balcony
    0.91
     doorway
    0.90
     deserted
    0.90
     canal
    0.89
    Activations Density 0.122%

    No Known Activations