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. 10380
    Prev
    Next
    INDEX
    Explanations

    statements indicating refusal to comment or share information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "declined."

    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
    è¦ļéĨĴ
    -0.73
    Ranked
    -0.71
    Offline
    -0.71
    ohyd
    -0.69
    ocratic
    -0.68
    =-=-=-=-=-=-=-=-
    -0.68
    agate
    -0.67
    facts
    -0.67
    stones
    -0.66
    types
    -0.65
    POSITIVE LOGITS
     Krug
    0.74
     miser
    0.73
     unanimously
    0.67
    CLASSIFIED
    0.65
     declines
    0.65
     admission
    0.64
     warr
    0.64
     hes
    0.63
     confir
    0.63
     sharply
    0.62
    Activations Density 0.016%

    No Known Activations