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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12029
    Prev
    Next
    INDEX
    Explanations

    specific references to technology products or components

    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
    Cause
    -0.85
    ERROR
    -0.81
    Population
    -0.80
    URI
    -0.77
    crime
    -0.76
    Crime
    -0.76
     contagious
    -0.75
    Political
    -0.74
     contag
    -0.73
    istical
    -0.73
    POSITIVE LOGITS
     Panasonic
    1.11
     Yamaha
    1.10
     Samsung
    1.01
     Asus
    1.00
     Motorola
    0.99
     Garmin
    0.98
     Jaguar
    0.98
     RX
    0.96
     Model
    0.95
     ASUS
    0.95
    Activations Density 0.296%

    No Known Activations