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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-RES-JB
    6. 11528
    Prev
    Next
    INDEX
    Explanations

    specific phrases enclosed in quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks and phrases enclosed within them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alger
    -0.70
     Nieto
    -0.69
     Azerb
    -0.68
     Choi
    -0.67
     viewers
    -0.65
     Gaal
    -0.64
     describ
    -0.64
     photographers
    -0.64
     upon
    -0.64
     Rica
    -0.63
    POSITIVE LOGITS
    classic
    1.29
    little
    1.17
    most
    1.14
    ordinary
    1.08
    official
    1.06
    technical
    1.06
    real
    1.04
    true
    1.03
    perfect
    1.03
    personal
    1.03
    Activations Density 0.068%

    No Known Activations