Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 12485
    Prev
    Next
    INDEX
    Explanations

    references to the state of Louisiana

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the state of Louisiana

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bsp
    -0.81
    ãĤ¯
    -0.81
    skirts
    -0.80
    ronic
    -0.79
    enegger
    -0.78
    ded
    -0.78
    posts
    -0.77
    ullah
    -0.76
    icle
    -0.76
    PsyNetMessage
    -0.75
    POSITIVE LOGITS
     Louisiana
    1.01
     Pelicans
    0.96
     Lafayette
    0.88
    iana
    0.87
     ILCS
    0.86
     Purchase
    0.86
     Parish
    0.79
    ©¶æ¥µ
    0.79
     Orleans
    0.76
     tyr
    0.74
    Activations Density 0.008%

    No Known Activations