© 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. 16844
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific location - "Cayman Islands"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Cayman Islands

    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
    selection
    -0.75
     Blink
    -0.68
    itbart
    -0.67
    ACTED
    -0.65
    izations
    -0.65
    é¾įå
    -0.63
    urgy
    -0.63
     Ashes
    -0.62
    iances
    -0.62
    ãĤ°
    -0.62
    POSITIVE LOGITS
     Cay
    1.11
    enne
    0.96
    uga
    0.91
    olla
    0.90
    alam
    0.87
    agna
    0.79
    atari
    0.79
    esian
    0.76
     Kong
    0.74
    oola
    0.72
    Activations Density 0.003%

    No Known Activations