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. 6-RES-JB
    6. 13596
    Prev
    Next
    INDEX
    Explanations

    references to development teams and creative individuals involved in various projects

    oai_token-act-pair · gpt-3.5-turbo

    information related to development teams and their achievements in project management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Trayvon
    -0.78
     measles
    -0.74
    tnc
    -0.73
    ibaba
    -0.72
    bia
    -0.71
     uninsured
    -0.71
     sting
    -0.70
    ratom
    -0.68
    jri
    -0.68
    aram
    -0.67
    POSITIVE LOGITS
     Studios
    1.06
     Animation
    1.00
     Publisher
    0.97
    isoft
    0.95
     Ubisoft
    0.95
     Developer
    0.93
     devs
    0.93
     Konami
    0.91
     Entertainment
    0.90
     studios
    0.88
    Activations Density 0.643%

    No Known Activations