© 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. 8-RES-JB
    11. 19339
    Prev
    Next
    INDEX
    Explanations

    mentions of the football team "Bournemouth" or similar spellings

    oai_token-act-pair · gpt-3.5-turbo

    references to specific sports teams or events

    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
    Effective
    -0.60
     Rossi
    -0.60
     Wid
    -0.56
     twin
    -0.56
    CONCLUS
    -0.55
    BIL
    -0.55
     RAD
    -0.55
    Wan
    -0.55
    RECT
    -0.54
     slic
    -0.54
    POSITIVE LOGITS
    emouth
    1.70
    oir
    1.17
    ourn
    1.05
    ettes
    1.02
    ette
    1.01
    itures
    0.98
    oyer
    0.97
    auts
    0.97
    iture
    0.96
    nette
    0.94
    Activations Density 0.040%

    No Known Activations