© 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. 16812
    Prev
    Next
    INDEX
    Explanations

    locations or landmarks related to the sea or water

    oai_token-act-pair · gpt-3.5-turbo

    references to marine ecosystems and geographical features related to coral reefs

    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
    ãĥł
    -0.73
    Chicago
    -0.72
    German
    -0.72
    CHO
    -0.71
    Germany
    -0.70
    chel
    -0.70
    CHA
    -0.70
    å¦
    -0.69
    Madison
    -0.68
    à¦
    -0.67
    POSITIVE LOGITS
     reef
    1.52
     Reef
    1.29
     reefs
    1.23
     aquarium
    1.09
     fisher
    0.85
     coral
    0.84
    er
    0.83
    Ħ¢
    0.82
     fisheries
    0.79
     inver
    0.77
    Activations Density 0.008%

    No Known Activations