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. 11-RES-JB
    6. 8385
    Prev
    Next
    INDEX
    Explanations

    pieces of text related to ratings or feedback

    oai_token-act-pair · gpt-3.5-turbo

    numeric values and ratings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eleph
    -0.71
     dotted
    -0.62
     oun
    -0.58
     weld
    -0.54
    etheless
    -0.54
    ò
    -0.53
     occas
    -0.53
     secretaries
    -0.53
    .""
    -0.52
     ®
    -0.51
    POSITIVE LOGITS
    Invalid
    0.72
    prem
    0.69
    dayName
    0.69
    PROV
    0.68
    Prev
    0.67
    thinkable
    0.67
    pmwiki
    0.66
    Posted
    0.65
    Rating
    0.64
    roo
    0.64
    Activations Density 0.367%

    No Known Activations