© 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. 19288
    Prev
    Next
    INDEX
    Explanations

    locations or bases of organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to locations or places where entities are situated

    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
     hurled
    -0.87
    umatic
    -0.85
     consumed
    -0.76
     wielded
    -0.75
    aped
    -0.75
     handed
    -0.75
    xual
    -0.74
    ŀ
    -0.74
     piled
    -0.74
    urd
    -0.73
    POSITIVE LOGITS
     conjunction
    1.09
     Vienna
    0.99
     Pasadena
    0.99
     Cambridge
    0.98
     Southeast
    0.98
     Bangalore
    0.98
     Omaha
    0.98
     Sicily
    0.97
     northwest
    0.96
     Cincinnati
    0.96
    Activations Density 0.161%

    No Known Activations