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. 10-RES-JB
    6. 15489
    Prev
    Next
    INDEX
    Explanations

    links to social media profiles

    oai_token-act-pair · gpt-3.5-turbo

    social media engagement and sharing prompts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mississ
    -0.67
    anon
    -0.65
    ickr
    -0.64
    Hamilton
    -0.63
     Finder
    -0.59
     Sask
    -0.57
    mouth
    -0.57
    ndum
    -0.56
     Elm
    -0.56
     Airways
    -0.56
    POSITIVE LOGITS
    TAG
    0.60
     Manson
    0.56
     respectful
    0.54
     therap
    0.53
     imprison
    0.51
    Cos
    0.51
    cks
    0.50
     smartest
    0.50
     celeb
    0.50
     Discovery
    0.49
    Activations Density 0.108%

    No Known Activations