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. 18062
    Prev
    Next
    INDEX
    Explanations

    legal and regulatory references, such as sections and laws

    oai_token-act-pair · gpt-3.5-turbo

    references to legal codes and regulations

    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
    emouth
    -0.79
    esses
    -0.78
    iser
    -0.76
    visors
    -0.73
    jee
    -0.71
    isers
    -0.69
    eness
    -0.69
     Tribunal
    -0.67
     desk
    -0.67
    assadors
    -0.64
    POSITIVE LOGITS
    §
    1.44
    Pg
    0.90
    Æ
    0.88
    ¶
    0.87
    Ëľ
    0.82
    UFC
    0.80
    Ranked
    0.78
    DIR
    0.76
    ©
    0.75
     Kund
    0.74
    Activations Density 0.008%

    No Known Activations