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. 10-RES-JB
    6. 22465
    Prev
    Next
    INDEX
    Explanations

    names of people on social media platforms

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals associated with various contexts or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     subdiv
    -0.76
    :,
    -0.74
    ',"
    -0.73
    "),
    -0.70
     favourable
    -0.67
     disadvantage
    -0.67
     certain
    -0.66
    '),
    -0.66
     exhibits
    -0.66
     favoured
    -0.66
    POSITIVE LOGITS
     (@
    2.36
     ðŁ
    1.47
     âľ
    1.35
    ðŁ
    1.30
     âĺ
    1.19
     âĿ
    1.15
    âľ
    1.15
    âĺ
    1.14
     ðŁij
    1.12
     ??
    1.10
    Activations Density 0.134%

    No Known Activations