© 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. 6-RES-JB
    11. 14534
    Prev
    Next
    INDEX
    Explanations

    references to the state of Nevada

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the state of Nevada

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fare
    -0.83
    notation
    -0.76
    orial
    -0.75
    umper
    -0.73
     pse
    -0.72
    NOT
    -0.68
    reads
    -0.68
    selage
    -0.64
    oured
    -0.64
    rers
    -0.64
    POSITIVE LOGITS
     Nevada
    0.78
     Coyotes
    0.75
     ranc
    0.72
     Territory
    0.69
    Nev
    0.69
     Reno
    0.68
     Vegas
    0.68
     crossings
    0.67
     caucuses
    0.67
     Nev
    0.66
    Activations Density 0.016%

    No Known Activations