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. 6-RES-JB
    6. 21279
    Prev
    Next
    INDEX
    Explanations

    user profiles with joining dates

    oai_token-act-pair · gpt-3.5-turbo

    metadata related to user profiles and blog activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andro
    -0.82
    oshenko
    -0.78
    onga
    -0.72
    agos
    -0.67
    acs
    -0.67
    banks
    -0.67
    coni
    -0.66
    awed
    -0.66
    ouf
    -0.64
    atically
    -0.64
    POSITIVE LOGITS
     Joined
    1.30
     Blog
    0.73
    âĸ¬
    0.69
     AZ
    0.68
     Rankings
    0.68
    çİĭ
    0.67
     Posts
    0.67
    ãĥ
    0.66
     Prediction
    0.65
     Eternal
    0.63
    Activations Density 0.014%

    No Known Activations