© 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. 17859
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Shannon"

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the name "Shannon" and related variations

    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
    icted
    -0.90
    dit
    -0.90
    ngth
    -0.86
    omething
    -0.81
    ¥µ
    -0.81
    ĻĤ
    -0.79
    hist
    -0.78
    undai
    -0.75
    heid
    -0.72
    osition
    -0.71
    POSITIVE LOGITS
     Shannon
    1.13
     Watts
    1.04
     Coulter
    0.87
    annon
    0.83
     Atkinson
    0.80
     Brands
    0.78
     Cooke
    0.77
     Briggs
    0.76
    ãĥ¥
    0.76
    ãĥ£
    0.75
    Activations Density 0.009%

    No Known Activations