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. 9-RES-JB
    6. 810
    Prev
    Next
    INDEX
    Explanations

    words or phrases emphasizing importance or specificity

    oai_token-act-pair · gpt-3.5-turbo

    the word "especially" and its variants, indicating emphasis or significance in a statement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hent
    -0.72
    ophys
    -0.72
    uble
    -0.70
    orc
    -0.69
    bridge
    -0.69
    hid
    -0.67
    ãĥ¼ãĥĨãĤ£
    -0.66
    retched
    -0.66
    alter
    -0.65
    pressed
    -0.64
    POSITIVE LOGITS
     considering
    1.06
     since
    0.97
     if
    0.83
     when
    0.82
     compared
    0.81
     pertaining
    0.78
     insofar
    0.77
     during
    0.76
     given
    0.76
     regarding
    0.76
    Activations Density 0.053%

    No Known Activations