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. 2582
    Prev
    Next
    INDEX
    Explanations

    references to specific numerical degrees or quantities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific timeframes or measurements related to the "60 Minutes" program

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ettings
    -0.78
    ifiable
    -0.75
    aukee
    -0.73
    achi
    -0.67
     Chronicle
    -0.63
    tern
    -0.61
     Flavoring
    -0.60
    hiba
    -0.59
     RTX
    -0.59
    alth
    -0.59
    POSITIVE LOGITS
     Minutes
    1.41
    fps
    1.15
    Hz
    1.14
    °
    1.12
     Seconds
    1.07
     degrees
    1.01
     Degree
    0.99
     degree
    0.96
     Hz
    0.95
    º
    0.94
    Activations Density 0.077%

    No Known Activations