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. 0-RES-JB
    6. 4021
    Prev
    Next
    INDEX
    Explanations

    words related to laws or regulations that are being passed or enacted

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "pass."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ogy
    -0.64
     Scale
    -0.62
     scope
    -0.61
     manufacture
    -0.61
     organ
    -0.59
     Weaver
    -0.59
     disorder
    -0.58
     Shapiro
    -0.57
     Scope
    -0.57
     stem
    -0.56
    POSITIVE LOGITS
    pass
    4.61
    Pass
    2.66
    PASS
    2.41
     PASS
    1.83
     Pass
    1.81
     pass
    1.68
     passes
    1.34
     Passing
    1.32
     passing
    1.30
     passed
    1.13
    Activations Density 0.012%

    No Known Activations