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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-RES-JB
    6. 14540
    Prev
    Next
    INDEX
    Explanations

    the name "Reed" written in sentences

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Reed."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expr
    -0.76
    icles
    -0.71
    AUT
    -0.71
    icle
    -0.68
     cars
    -0.67
     en
    -0.66
     che
    -0.66
    Hit
    -0.65
    cheat
    -0.65
     enc
    -0.62
    POSITIVE LOGITS
     Reed
    4.04
     Reynolds
    1.17
     Rosenberg
    1.16
     Ridley
    1.16
     Redmond
    1.13
     Dunn
    1.12
     Draper
    1.12
     Reid
    1.12
     Rudd
    1.10
     Richards
    1.08
    Activations Density 0.013%

    No Known Activations