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. 2-RES-JB
    6. 2735
    Prev
    Next
    INDEX
    Explanations

    keywords related to enhancements, improvements, or positive additions

    oai_token-act-pair · gpt-3.5-turbo

    words related to various types of "ments," indicating actions or conditions, such as government and academic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sw
    -0.74
    \\\\\\\\
    -0.71
    ²¾
    -0.68
    ãĥ£
    -0.64
    Reviewer
    -0.61
    ãĥį
    -0.58
     lif
    -0.58
     bread
    -0.58
    non
    -0.58
     striking
    -0.58
    POSITIVE LOGITS
    poons
    1.24
    omething
    1.18
    uits
    1.06
    mith
    1.05
    poon
    1.05
    ilver
    1.04
    hirt
    1.03
    peed
    1.03
    pring
    1.00
    cape
    1.00
    Activations Density 0.054%

    No Known Activations