Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 15697
    Prev
    Next
    INDEX
    Explanations

    phrases relating to credibility, reputation, and trust

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heny
    -0.87
     Ago
    -0.85
     motions
    -0.70
     Architecture
    -0.70
    chen
    -0.69
    chens
    -0.68
     cabinets
    -0.67
    nels
    -0.66
    cart
    -0.65
    ugal
    -0.65
    POSITIVE LOGITS
     diminished
    1.06
     shaken
    1.04
     shaky
    1.04
     undermined
    1.04
     deteriorated
    1.02
     doubted
    1.02
     waning
    1.01
     eroded
    1.00
     weakened
    0.99
     deteriorating
    0.99
    Activations Density 0.244%

    No Known Activations