© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 22725
    Prev
    Next
    INDEX
    Explanations

    the word "Comet" with differing levels of relevance or importance

    oai_token-act-pair · gpt-3.5-turbo

    references to comets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mah
    -0.85
    SL
    -0.79
     Lank
    -0.75
     Forrest
    -0.75
    OOD
    -0.72
    DR
    -0.71
     rand
    -0.70
     handic
    -0.70
     Rand
    -0.69
     trunk
    -0.68
    POSITIVE LOGITS
     comet
    3.86
     Comet
    3.74
     Pluto
    1.36
     asteroids
    1.22
     Ceres
    1.19
     meteor
    1.18
     nucleus
    1.17
     Collider
    1.16
     Jupiter
    1.16
     asteroid
    1.14
    Activations Density 0.032%

    No Known Activations