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. 3-RES-JB
    6. 6644
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Chandler", with extra emphasis on the specific occurrence of "Chandler" for activation level 10

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals associated with specific actions or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.93
     Cosponsors
    -0.89
    ration
    -0.88
    uga
    -0.84
    tro
    -0.84
    ution
    -0.82
    culosis
    -0.78
    odon
    -0.77
    lain
    -0.75
    iform
    -0.75
    POSITIVE LOGITS
     Parsons
    0.85
     Chandler
    0.77
    olph
    0.74
    eting
    0.74
     Stephenson
    0.72
     Harden
    0.72
     Schr
    0.72
    agne
    0.71
     Randolph
    0.70
    otle
    0.70
    Activations Density 0.018%

    No Known Activations