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. 1-RES-JB
    6. 19322
    Prev
    Next
    INDEX
    Explanations

    references to social media platforms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the social media platform Pinterest

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scrimmage
    -0.66
    ~~~~~~~~
    -0.66
    ppo
    -0.65
    lves
    -0.65
    eb
    -0.64
    igh
    -0.63
    Lex
    -0.60
    ocent
    -0.60
    åĤ
    -0.59
    ×Ļ×
    -0.58
    POSITIVE LOGITS
     Pinterest
    1.34
    ileaks
    0.91
    acebook
    0.83
    atchewan
    0.81
    ulkan
    0.77
    Pinterest
    0.75
    etsy
    0.75
    psey
    0.73
    sylv
    0.71
    vine
    0.71
    Activations Density 0.006%

    No Known Activations