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

    Neuronpedia

    APICircuit 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. 2-RES-JB
    6. 19156
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Bartlett."

    oai_token-act-pair · gpt-3.5-turbo

    repeated appearances of the substring "lett," indicating a focus on a specific topic or name associated with that term

    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
    govtrack
    -0.75
    senal
    -0.75
    abuse
    -0.70
    ModLoader
    -0.70
    demand
    -0.69
    ccording
    -0.68
    condition
    -0.66
    Þ
    -0.65
    EStream
    -0.64
     AQ
    -0.64
    POSITIVE LOGITS
    lett
    1.24
    sburgh
    1.07
    esy
    0.83
    sburg
    0.83
    stown
    0.82
     Township
    0.78
    endor
    0.77
    anie
    0.76
    eno
    0.75
    itude
    0.75
    Activations Density 0.010%

    No Known Activations