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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11556
    Prev
    Next
    INDEX
    Explanations

    references to a group of individuals working together in a specific context, particularly crew members

    oai_token-act-pair · gpt-3.5-turbo

    references to a group of individuals involved in a specific activity or situation

    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
     ISI
    -0.64
     Bout
    -0.63
    ashtra
    -0.62
     Fasc
    -0.62
     Tend
    -0.62
     Lent
    -0.62
     Marketable
    -0.61
    utterstock
    -0.60
    æĺ
    -0.60
    ãĥ¤
    -0.59
    POSITIVE LOGITS
    members
    1.78
    member
    1.58
    mates
    1.38
     members
    1.13
     member
    1.11
    wreck
    1.02
    mate
    1.00
     mates
    0.99
    men
    0.94
    smanship
    0.92
    Activations Density 0.026%

    No Known Activations