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. 8068
    Prev
    Next
    INDEX
    Explanations

    content related to environmental pollution and contaminants

    oai_token-act-pair · gpt-3.5-turbo

    mentions of hazardous substances and environmental factors

    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
    –
    -1.45
    .–
    -1.30
    )—
    -1.25
    —"
    -1.17
    —
    -1.16
    âĢIJ
    -1.11
    —-
    -1.09
     âμ
    -0.97
    ±
    -0.93
    "—
    -0.92
    POSITIVE LOGITS
     ...
    2.49
     ....
    2.27
     ..."
    2.15
     ......
    2.14
     ..
    1.77
     ........
    1.62
     [...]
    1.44
     ..............
    1.44
     ..........
    1.44
     ................
    1.35
    Activations Density 0.205%

    No Known Activations