© 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. 1-RES-JB
    11. 20254
    Prev
    Next
    INDEX
    Explanations

    instances of the word "communal" along with related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to communal aspects and interactions within society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wives
    -0.73
    ा
    -0.72
     Heidi
    -0.70
    abl
    -0.70
    acea
    -0.68
    manship
    -0.67
    aneers
    -0.67
    geries
    -0.66
    ahead
    -0.65
    OTUS
    -0.65
    POSITIVE LOGITS
     communal
    1.20
     fodder
    0.74
    theless
    0.72
     grievances
    0.70
    ivities
    0.69
     largeDownload
    0.69
    halla
    0.68
     sewer
    0.65
     sep
    0.65
     recol
    0.65
    Activations Density 0.016%

    No Known Activations