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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9192
    Prev
    Next
    INDEX
    Explanations

    terms related to information technology and operations

    oai_token-act-pair · gpt-3.5-turbo

    themes related to governance and societal structures

    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
    $.
    -0.61
    +.
    -0.60
    iatus
    -0.57
    stasy
    -0.56
    DonaldTrump
    -0.56
    ilaterally
    -0.54
    endon
    -0.53
    !.
    -0.52
     LLP
    -0.52
     Helpful
    -0.51
    POSITIVE LOGITS
     consists
    0.92
     consisted
    0.89
     seems
    0.71
     seemed
    0.70
     isn
    0.68
     relies
    0.68
     includes
    0.68
     hasn
    0.68
     varies
    0.67
     is
    0.67
    Activations Density 0.725%

    No Known Activations