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. 19356
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific features or elements within a designated structure

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns and phrases indicating organizations or structured groups

    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
    µ
    -0.62
    named
    -0.60
    å¦
    -0.59
     Marketable
    -0.58
    éĽ
    -0.57
    Ĭ
    -0.56
    è¦
    -0.56
     Nanto
    -0.55
    ãĥĩãĤ£
    -0.55
     Kurd
    -0.54
    POSITIVE LOGITS
    's
    1.37
    ÃŃs
    0.93
     into
    0.91
    ´
    0.80
     financially
    0.78
     territ
    0.77
     anew
    0.76
     finances
    0.76
     accordingly
    0.74
     through
    0.74
    Activations Density 0.604%

    No Known Activations