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. 3-RES-JB
    6. 2512
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize a conclusion or important point

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "bottom line."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -0.84
    ãĥ¼ãĥĨãĤ£
    -0.81
    ãĥĥ
    -0.76
    ãĥ¼ãĥĨ
    -0.73
    ãĥĺ
    -0.70
    è£ħ
    -0.70
    Known
    -0.69
    DOM
    -0.68
     UCHIJ
    -0.68
    è¦ļéĨĴ
    -0.67
    POSITIVE LOGITS
    lines
    0.82
     Lines
    0.77
    holders
    0.75
     LINE
    0.73
     lines
    0.70
    line
    0.70
     margin
    0.70
     margins
    0.68
     line
    0.64
    rolley
    0.62
    Activations Density 0.042%

    No Known Activations