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. 4314
    Prev
    Next
    INDEX
    Explanations

    words related to discussing various complex issues or topics

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to mental health, societal issues, and significant challenges

    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
    ãĥīãĥ©
    -0.87
    racuse
    -0.81
    issions
    -0.78
    ãĥİ
    -0.68
    ãĥ¼ãĥ³
    -0.66
    å§«
    -0.64
    ods
    -0.64
    encia
    -0.63
    actionDate
    -0.63
    =]
    -0.63
    POSITIVE LOGITS
     we
    0.92
     borne
    0.90
     discussed
    0.90
     I
    0.86
     alluded
    0.86
     explored
    0.82
     sorely
    0.81
     inherent
    0.81
     mentioned
    0.80
     which
    0.80
    Activations Density 0.444%

    No Known Activations