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. 16194
    Prev
    Next
    INDEX
    Explanations

    references to a specific person or entity named "Dimon"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Dimon"

    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
     citation
    -0.73
     corpus
    -0.71
     annotations
    -0.68
    lege
    -0.67
     avalanche
    -0.66
     endorsement
    -0.66
    Ħ¢
    -0.65
     alive
    -0.65
     scholarship
    -0.65
     citizenship
    -0.65
    POSITIVE LOGITS
     Dim
    4.08
    Dim
    2.88
    dim
    1.91
     Dmit
    1.44
     dim
    1.14
     Bald
    1.08
     Dum
    1.07
     Var
    1.07
     Sever
    1.03
     Madd
    1.03
    Activations Density 0.028%

    No Known Activations