© 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
    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. 7667
    Prev
    Next
    INDEX
    Explanations

    locations or proper nouns mentioning "Shore"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific locations or names associated with "Shore."

    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
    arcity
    -0.93
    ibles
    -0.90
    ible
    -0.88
    orate
    -0.87
    ivia
    -0.87
    ibility
    -0.86
    orescent
    -0.81
    ombs
    -0.78
    olkien
    -0.78
    ence
    -0.78
    POSITIVE LOGITS
     Shore
    1.32
    bone
    0.85
     Island
    0.84
     Islands
    0.82
     Howe
    0.81
    brook
    0.79
     Beach
    0.78
    lake
    0.78
    ¯¯¯¯
    0.77
    stals
    0.76
    Activations Density 0.008%

    No Known Activations