© 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. 9308
    Prev
    Next
    INDEX
    Explanations

    references to the state of Florida

    oai_token-act-pair · gpt-3.5-turbo

    references to Florida and its residents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Redemption
    -0.76
    selves
    -0.75
     bulls
    -0.74
    PC
    -0.71
    CHR
    -0.65
     buckle
    -0.64
     Shack
    -0.64
     orally
    -0.64
    STD
    -0.61
    ELL
    -0.60
    POSITIVE LOGITS
    hess
    0.92
     Flor
    0.91
    idian
    0.90
    ertodd
    0.89
    iculture
    0.85
    ifer
    0.82
    asma
    0.82
    issance
    0.81
    Flor
    0.80
    iage
    0.79
    Activations Density 0.006%

    No Known Activations