© 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. 10-RES-JB
    11. 20431
    Prev
    Next
    INDEX
    Explanations

    words related to technical specifications and equipment maintenance

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms that represent organizations or components

    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
     Frey
    -0.75
     Afric
    -0.72
     Trayvon
    -0.69
     âĢ¦"
    -0.68
     Zucker
    -0.68
     drunk
    -0.67
     thereto
    -0.65
     negro
    -0.65
     Tacoma
    -0.65
     AMERICA
    -0.62
    POSITIVE LOGITS
    ipment
    1.17
    autions
    1.15
    ailability
    1.14
    chieve
    1.12
    rodu
    1.12
    requency
    1.07
    reenshots
    1.04
     Requirements
    1.02
    perties
    1.00
    Requirements
    0.99
    Activations Density 0.257%

    No Known Activations