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. 17749
    Prev
    Next
    INDEX
    Explanations

    phrases referring to a group or collection of items or entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that start with "These" followed by numerical identifiers

    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
    terness
    -0.80
    opus
    -0.74
    obook
    -0.73
    onement
    -0.73
    let
    -0.72
     Pwr
    -0.71
    owder
    -0.71
    irlf
    -0.71
    iever
    -0.71
    lev
    -0.71
    POSITIVE LOGITS
     kinds
    1.12
     developments
    1.11
     findings
    1.10
     are
    1.10
     include
    1.09
     aren
    1.06
     considerations
    1.05
     occurrences
    1.05
     observations
    1.05
     types
    1.05
    Activations Density 0.101%

    No Known Activations