© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 9990
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "and," often connecting different pieces of information or clauses

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" used in various contexts

    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
    plex
    -0.64
    pires
    -0.60
    ppa
    -0.60
    clad
    -0.59
    spir
    -0.59
    steam
    -0.58
    burgh
    -0.58
    ãĥ¼ãĥ
    -0.58
    utenberg
    -0.56
    veland
    -0.55
    POSITIVE LOGITS
     nor
    1.50
     neither
    1.41
     therefore
    1.39
     consequently
    1.38
     Nor
    1.33
     furthermore
    1.29
     hence
    1.24
     moreover
    1.24
     certainly
    1.23
     thus
    1.23
    Activations Density 0.188%

    No Known Activations