Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 6436
    Prev
    Next
    INDEX
    Explanations

    GitHub repositories

    oai_token-act-pair · gpt-3.5-turbo

    mentions of GitHub in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lling
    -0.85
    ewitness
    -0.83
    estinal
    -0.78
    igslist
    -0.77
    ecause
    -0.71
    berman
    -0.69
    vation
    -0.68
    undai
    -0.68
    cum
    -0.67
    atonin
    -0.66
    POSITIVE LOGITS
    usercontent
    1.01
     repositories
    1.00
     repository
    0.99
     repo
    0.88
    github
    0.86
     Pages
    0.80
    docs
    0.72
    itory
    0.71
     Contribut
    0.70
    ãĤĮ
    0.69
    Activations Density 0.016%

    No Known Activations