© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7-RES-JB
    11. 14571
    Prev
    Next
    INDEX
    Explanations

    terms related to the geographical region of the Arctic

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Arctic."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enance
    -1.12
    ership
    -0.98
    ister
    -0.95
    advertising
    -0.89
    iard
    -0.86
    efer
    -0.85
    reads
    -0.82
    reviewed
    -0.81
    ible
    -0.81
    eric
    -0.81
    POSITIVE LOGITS
     Circle
    0.98
     warming
    0.96
    thur
    0.94
     Sunrise
    0.94
     Ocean
    0.90
     amplification
    0.87
     biome
    0.79
     winters
    0.78
     Sea
    0.76
     ozone
    0.76
    Activations Density 0.020%

    No Known Activations