© 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. 20119
    Prev
    Next
    INDEX
    Explanations

    specific locations or places, often related to travel or destinations

    oai_token-act-pair · gpt-3.5-turbo

    references to various travel destinations

    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
    croft
    -0.88
    aps
    -0.84
    IGHTS
    -0.83
    appa
    -0.79
    ells
    -0.75
    ooks
    -0.75
    aver
    -0.74
    ighters
    -0.71
    opes
    -0.69
    ights
    -0.69
    POSITIVE LOGITS
     destination
    1.25
     Destination
    1.25
     destinations
    0.98
     whence
    0.78
    dest
    0.77
     Afric
    0.74
     traveler
    0.72
     haunt
    0.71
     abroad
    0.69
     Kuala
    0.67
    Activations Density 0.006%

    No Known Activations