© 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. 8-RES-JB
    11. 20165
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Heathrow"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific location or person, particularly focused on "Heathrow."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antine
    -0.80
    ances
    -0.77
    itive
    -0.74
    士
    -0.73
    pmwiki
    -0.73
    ãĥ£
    -0.73
    ably
    -0.71
    hement
    -0.70
    amination
    -0.69
    afort
    -0.68
    POSITIVE LOGITS
    gow
    0.91
    otle
    0.76
    TERN
    0.72
    MET
    0.67
     Ames
    0.66
    sheets
    0.66
    brow
    0.66
     McF
    0.65
    cig
    0.65
    vine
    0.64
    Activations Density 0.093%

    No Known Activations