© 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. 1-RES-JB
    11. 18005
    Prev
    Next
    INDEX
    Explanations

    phrases related to North America and its various aspects such as players, internet architecture, and EP scores

    oai_token-act-pair · gpt-3.5-turbo

    references to North America and specific organizations or agreements related to it

    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
    draw
    -0.89
     Stard
    -0.83
    gets
    -0.81
    notes
    -0.78
    tons
    -0.78
    =-=-=-=-=-=-=-=-
    -0.74
    Tea
    -0.74
    tones
    -0.71
    ãĤ¼
    -0.69
    sets
    -0.69
    POSITIVE LOGITS
     LCS
    1.09
     NA
    1.06
    heast
    1.02
    ZI
    1.02
    heastern
    0.88
    ICAN
    0.88
    ESE
    0.76
    ACP
    0.74
    WER
    0.74
    ICE
    0.74
    Activations Density 0.004%

    No Known Activations