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. 152
    Prev
    Next
    INDEX
    Explanations

    words related to the name "MacCarthy" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "thy" in various contexts

    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
     bloc
    -0.89
     Flash
    -0.79
     Blues
    -0.72
     flash
    -0.71
     dorm
    -0.70
     Courier
    -0.69
     Buc
    -0.68
     Colleg
    -0.67
     Confederate
    -0.66
     Civil
    -0.66
    POSITIVE LOGITS
    thy
    4.28
    ikh
    1.64
    othy
    1.46
     Thy
    1.45
     thyroid
    1.30
     thy
    1.10
    adh
    1.03
    lesi
    1.02
    lip
    0.99
     KH
    0.98
    Activations Density 0.036%

    No Known Activations