© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 8290
    Prev
    Next
    INDEX
    Explanations

    mentions of the state of Arizona

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uther
    -0.83
    hare
    -0.82
    ãĤ¼ãĤ¦ãĤ¹
    -0.80
    pite
    -0.78
    fare
    -0.76
    flows
    -0.73
    itness
    -0.73
    ructure
    -0.73
    big
    -0.72
    isters
    -0.72
    POSITIVE LOGITS
     Coyotes
    1.16
     Cardinals
    1.08
     Arizona
    0.93
     State
    0.88
     AZ
    0.83
     Mesa
    0.83
    illo
    0.82
     Springs
    0.82
     Revised
    0.82
     Republic
    0.81
    Activations Density 0.013%

    No Known Activations