© 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. 0-RES-JB
    11. 1119
    Prev
    Next
    INDEX
    Explanations

    terms related to grouping or clustering of items or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to clusters in various contexts

    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
    Sav
    -0.74
     Honest
    -0.70
    Anim
    -0.70
     Anim
    -0.70
     Taxes
    -0.69
    Honest
    -0.68
    piration
    -0.68
    anim
    -0.66
    roy
    -0.66
    printed
    -0.66
    POSITIVE LOGITS
     cluster
    3.76
     clusters
    2.79
     Cluster
    2.74
     clust
    2.04
     clustered
    1.96
     swarm
    1.39
     constellation
    1.31
     grouping
    1.10
     node
    1.03
     nodes
    1.03
    Activations Density 0.009%

    No Known Activations