© 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. 0-RES-JB
    11. 8176
    Prev
    Next
    INDEX
    Explanations

    references to the state of Arizona

    oai_token-act-pair · gpt-3.5-turbo

    references to the state of Arizona

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     labou
    -0.79
     downwards
    -0.76
     Notting
    -0.74
     gren
    -0.72
    chel
    -0.71
     cords
    -0.71
     Fou
    -0.67
     organise
    -0.67
     liter
    -0.66
     labour
    -0.65
    POSITIVE LOGITS
     Arizona
    3.63
    Arizona
    3.34
     Tucson
    2.41
     AZ
    2.02
     Colorado
    1.97
     Nevada
    1.94
     Oregon
    1.92
     Arkansas
    1.89
    Colorado
    1.89
     Utah
    1.89
    Activations Density 0.016%

    No Known Activations