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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 17294
    Prev
    Next
    INDEX
    Explanations

    legal or investigative terminology

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to legal and procedural contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     domest
    -0.61
    obyl
    -0.60
    interstitial
    -0.60
     roofs
    -0.60
     scenic
    -0.59
    animate
    -0.58
     indoors
    -0.57
     conserve
    -0.56
     skysc
    -0.56
     flowering
    -0.55
    POSITIVE LOGITS
     redacted
    0.84
     wording
    0.82
     contradicted
    0.76
     furthermore
    0.74
     Counsel
    0.73
    Response
    0.72
     quoting
    0.72
    Comment
    0.71
     asserted
    0.71
     inconsistencies
    0.70
    Activations Density 2.175%

    No Known Activations