© 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 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. 7-RES-JB
    11. 20710
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'Rams' referencing a sports team

    oai_token-act-pair · gpt-3.5-turbo

    references to the Rams football team

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     showc
    -0.64
    umerable
    -0.63
    judicial
    -0.63
     grat
    -0.61
     uranium
    -0.61
    ternity
    -0.60
     coronary
    -0.60
    CLASSIFIED
    -0.60
     opaque
    -0.59
     disadvant
    -0.58
    POSITIVE LOGITS
    aic
    0.99
    mers
    0.94
     Rams
    0.93
    eco
    0.92
    der
    0.88
    den
    0.86
    ming
    0.84
    borg
    0.81
    oran
    0.81
    gaard
    0.79
    Activations Density 0.043%

    No Known Activations