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. 4-RES-JB
    6. 5172
    Prev
    Next
    INDEX
    Explanations

    keywords related to governmental or organizational programs or initiatives

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various schemes or programs

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

    No Comments

    Negative Logits
    Flo
    -0.65
     Clover
    -0.61
    Rated
    -0.58
     Hond
    -0.58
     Hug
    -0.57
     Flo
    -0.56
    cknowled
    -0.56
     Idle
    -0.56
    inas
    -0.55
     separatist
    -0.55
    POSITIVE LOGITS
     scheme
    1.10
     schemes
    1.08
    ĸļ
    1.04
    eering
    0.85
     devised
    0.82
    ulence
    0.82
    eers
    0.80
    etary
    0.80
     Scheme
    0.80
    matic
    0.76
    Activations Density 0.011%

    No Known Activations