© 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. 2-RES-JB
    11. 17766
    Prev
    Next
    INDEX
    Explanations

    references to shared or communal spaces and activities

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to communal structures and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    manship
    -0.78
    geries
    -0.78
    sein
    -0.75
    wives
    -0.69
    then
    -0.69
    ym
    -0.67
    KO
    -0.67
    metics
    -0.67
    ggies
    -0.66
    thens
    -0.66
    POSITIVE LOGITS
     communal
    1.09
    ised
    0.79
    halla
    0.78
    ized
    0.78
     harmony
    0.77
     affili
    0.75
     minded
    0.75
     fodder
    0.75
     cohesion
    0.72
    ãĥ¥
    0.71
    Activations Density 0.014%

    No Known Activations