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. 4257
    Prev
    Next
    INDEX
    Explanations

    words related to a specific individual named Korenic

    oai_token-act-pair · gpt-3.5-turbo

    the recurring mention of a specific name or identity, likely related to an individual involved in criminal activity

    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
     sheep
    -0.72
     Heal
    -0.70
     Arrows
    -0.69
     Dunham
    -0.64
     Lowry
    -0.64
     Bullets
    -0.61
    ffect
    -0.60
     Remote
    -0.59
     Burnett
    -0.58
     Done
    -0.58
    POSITIVE LOGITS
    nic
    4.38
    Nic
    1.79
    nia
    1.61
    gi
    1.41
     nic
    1.23
     Nic
    1.14
    tin
    1.08
    thia
    1.07
    nc
    1.05
    nik
    1.03
    Activations Density 0.020%

    No Known Activations