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. 7-RES-JB
    6. 12794
    Prev
    Next
    INDEX
    Explanations

    interactions and engagement prompts

    oai_token-act-pair · gpt-3.5-turbo

    requests for audience engagement and feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nato
    -0.67
     1976
    -0.60
    ³³³³³³³³
    -0.59
     repud
    -0.59
    gain
    -0.58
     1979
    -0.58
     1972
    -0.58
     1961
    -0.58
     Klux
    -0.57
    Ͻ
    -0.56
    POSITIVE LOGITS
     ;)
    1.05
     :)
    0.99
     ðŁĻĤ
    0.93
     :-)
    0.78
    )!
    0.76
     upcoming
    0.75
     yours
    0.75
     goodies
    0.75
     hopefully
    0.73
     ðŁĺ
    0.71
    Activations Density 1.109%

    No Known Activations