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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 23582
    Prev
    Next
    INDEX
    Explanations

    words related to a specific person, "Reynolds"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Reynolds."

    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
     theft
    -0.71
     thief
    -0.66
     aur
    -0.65
    Ability
    -0.64
     sabotage
    -0.64
    celona
    -0.64
    bar
    -0.63
     sab
    -0.63
     goal
    -0.63
     Azerbai
    -0.62
    POSITIVE LOGITS
     Reynolds
    4.23
     Reyn
    1.30
     Reeves
    1.27
     Rowe
    1.20
     Reese
    1.19
     Dunn
    1.15
     Browne
    1.14
     Scully
    1.14
     Vaugh
    1.13
     Higgins
    1.13
    Activations Density 0.017%

    No Known Activations