© 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
    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. 21402
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Volunteer" or related terms with variations in case

    oai_token-act-pair · gpt-3.5-turbo

    references to volumes and their related topics

    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
     franc
    -0.68
     Sunder
    -0.63
     Rampage
    -0.62
     prem
    -0.62
    LESS
    -0.60
     Rebels
    -0.58
     NIC
    -0.58
     pods
    -0.57
     Franks
    -0.56
     Fallen
    -0.55
    POSITIVE LOGITS
    untary
    1.58
    atile
    1.57
    atility
    1.50
    umes
    1.37
    untarily
    1.35
    unte
    1.27
    cano
    1.24
    leys
    1.15
    UME
    1.11
    umin
    1.10
    Activations Density 0.038%

    No Known Activations