© 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 EvalsExportsAPI 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. 10-RES-JB
    11. 3456
    Prev
    Next
    INDEX
    Explanations

    names of individuals, places, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to individuals and their roles or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     indeed
    -0.51
     :(
    -0.50
     teasing
    -0.50
     ðŁij
    -0.50
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.50
     flavours
    -0.49
     festive
    -0.49
     gloomy
    -0.49
     flavour
    -0.48
     disbel
    -0.47
    POSITIVE LOGITS
    negie
    0.61
     thereto
    0.60
    hiba
    0.55
    .).
    0.52
     Associates
    0.52
    interstitial
    0.52
    )."
    0.52
    unct
    0.51
    ]."
    0.50
    ighthouse
    0.49
    Activations Density 1.079%

    No Known Activations