Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 3565
    Prev
    Next
    INDEX
    Explanations

    phrases related to involvement or collaboration with others

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols often associated with emphasis or emotion

    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
     Droid
    -0.52
     cyan
    -0.50
     Pilgrim
    -0.50
     Libyan
    -0.50
     scatter
    -0.49
     Belg
    -0.48
     Voyager
    -0.48
     relay
    -0.48
     scattering
    -0.48
     paternal
    -0.48
    POSITIVE LOGITS
    ¹
    1.10
    ı
    1.08
    Į
    1.08
    ¬
    1.08
    Ĵ
    1.04
    ¡
    1.04
    ª
    1.02
    ł
    1.01
    ²
    1.00
    ¿
    0.97
    Activations Density 0.496%

    No Known Activations