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. 11-RES-JB
    6. 10455
    Prev
    Next
    INDEX
    Explanations

    informational reports or news

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "reports" or similar terms indicating the dissemination of information or news

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hetics
    -0.65
    utical
    -0.60
    tons
    -0.59
    ternity
    -0.59
    Textures
    -0.59
    imus
    -0.58
    drivers
    -0.58
    unin
    -0.57
    artist
    -0.56
    appropriately
    -0.55
    POSITIVE LOGITS
     alleging
    1.17
     surfaced
    1.14
     suggesting
    1.11
     claiming
    1.06
     indicating
    1.05
     circulating
    1.04
     circulated
    1.02
     linking
    0.98
     indicate
    0.98
     stating
    0.98
    Activations Density 0.142%

    No Known Activations