© 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. 4133
    Prev
    Next
    INDEX
    Explanations

    locations and international references

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations and 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
     predec
    -0.67
     incent
    -0.66
    epad
    -0.62
     minions
    -0.62
    emo
    -0.62
    aqu
    -0.61
    rity
    -0.61
     greed
    -0.61
    acles
    -0.61
     mustache
    -0.61
    POSITIVE LOGITS
    ESE
    0.83
     Province
    0.83
    Ô
    0.76
    where
    0.75
     Foreign
    0.75
     Tourism
    0.73
     tourist
    0.73
     consulate
    0.72
     Railway
    0.72
     imports
    0.70
    Activations Density 0.732%

    No Known Activations