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. 8-RES-JB
    6. 2975
    Prev
    Next
    INDEX
    Explanations

    discussions related to laws and regulations

    oai_token-act-pair · gpt-3.5-turbo

    themes related to the need for legal and governmental reforms aimed at protecting rights and ensuring accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fame
    -0.60
     Gleaming
    -0.59
    \-
    -0.59
     Fancy
    -0.58
    liner
    -0.57
     Mehran
    -0.56
    tick
    -0.55
    renheit
    -0.55
    assium
    -0.54
    bare
    -0.53
    POSITIVE LOGITS
     urgently
    0.94
     accountable
    0.85
     ASAP
    0.85
     equitable
    0.84
     responsibly
    0.81
     accountability
    0.81
     transparency
    0.80
     reforms
    0.78
    cknow
    0.78
     policymakers
    0.77
    Activations Density 1.302%

    No Known Activations