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. 24050
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Vendetti"

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals or surnames

    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
     ins
    -0.64
     alt
    -0.64
     remote
    -0.64
     hop
    -0.63
     sur
    -0.63
     sin
    -0.62
     brow
    -0.62
     accessible
    -0.61
     Eth
    -0.61
     Monarch
    -0.60
    POSITIVE LOGITS
    etti
    4.56
    otti
    1.48
    ucci
    1.47
    etta
    1.40
    ieri
    1.38
    acci
    1.28
    olini
    1.26
    elli
    1.25
    ini
    1.23
    ello
    1.14
    Activations Density 0.010%

    No Known Activations