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. 3-RES-JB
    6. 1367
    Prev
    Next
    INDEX
    Explanations

    references to political systems or structures and related ideas like cooperation, negotiation, and dominance

    oai_token-act-pair · gpt-3.5-turbo

    references to systemic structures or frameworks, particularly in relation to governance or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.80
    æĢ
    -0.79
    ãĤ¤ãĥĪ
    -0.78
    ishable
    -0.75
    spell
    -0.71
     earnest
    -0.70
    fle
    -0.65
    noon
    -0.64
    past
    -0.63
    sbm
    -0.62
    POSITIVE LOGITS
    atics
    1.13
    ologies
    0.87
    atically
    0.85
     integ
    0.82
    atic
    0.77
    eering
    0.75
    ically
    0.74
    atism
    0.72
     governing
    0.72
     rigged
    0.71
    Activations Density 0.038%

    No Known Activations