Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 0-RES-JB
    6. 11203
    Prev
    Next
    INDEX
    Explanations

    verbs related to gathering or mobilizing people or resources for a specific purpose

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "muster" and its variations, along with related terms suggesting gathering or assembling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itch
    -0.67
     Spaces
    -0.66
    icle
    -0.66
    rique
    -0.63
     Trees
    -0.62
    ologies
    -0.62
    alias
    -0.62
     Practices
    -0.61
    rosso
    -0.60
     Bend
    -0.60
    POSITIVE LOGITS
     muster
    1.95
    zed
    1.83
    awed
    1.65
    bledon
    1.50
     compartment
    1.26
    ered
    1.26
    xc
    1.25
    loaded
    1.22
    ighed
    1.19
    xd
    1.02
    Activations Density 0.035%

    No Known Activations