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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 4492
    Prev
    Next
    INDEX
    Explanations

    monetary and administrative terms, such as subsidies, agreements, and authority

    oai_token-act-pair · gpt-3.5-turbo

    significant nouns and terms related to economic and legal contexts

    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
    dden
    -0.65
    Redd
    -0.64
    racuse
    -0.64
    ZI
    -0.63
    joice
    -0.62
     Jaw
    -0.61
     Tablet
    -0.60
     Lonely
    -0.60
     Trou
    -0.60
     Ey
    -0.59
    POSITIVE LOGITS
     consisted
    0.92
     includes
    0.83
     include
    0.76
     consists
    0.76
     may
    0.73
     manifests
    0.71
     amounted
    0.71
     extends
    0.70
     expired
    0.70
    nings
    0.70
    Activations Density 0.231%

    No Known Activations