© 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. 8-RES-JB
    11. 12573
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific medical condition or abbreviation "MC"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Marvel Cinematic Universe (MCU) and its related elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rees
    -0.71
     Meier
    -0.67
     Bauer
    -0.64
    away
    -0.62
    glass
    -0.62
    ochet
    -0.61
    alion
    -0.59
     Bentley
    -0.59
     stra
    -0.59
    lift
    -0.59
    POSITIVE LOGITS
    ORPG
    1.15
    ONEY
    0.88
    IAS
    0.78
    ategory
    0.74
    rals
    0.74
    hattan
    0.74
    ambo
    0.72
    ĺħ
    0.72
    ovember
    0.72
    joy
    0.70
    Activations Density 0.072%

    No Known Activations