© 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. 9-RES-JB
    11. 2559
    Prev
    Next
    INDEX
    Explanations

    references to religious beliefs or practices

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    µ
    -0.77
    ģĸ
    -0.74
    Ĥİ
    -0.72
    ©¶æ
    -0.66
    ±
    -0.65
    £
    -0.64
    ateur
    -0.62
    ½
    -0.62
    ¢
    -0.60
    Ļ½
    -0.60
    POSITIVE LOGITS
     presence
    1.01
     involvement
    0.94
     occupies
    0.93
     designation
    0.88
     sightings
    0.85
     sighting
    0.80
     exists
    0.79
     disappears
    0.79
     Presence
    0.78
     inclusion
    0.78
    Activations Density 0.643%

    No Known Activations