© 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. 10-RES-JB
    11. 12806
    Prev
    Next
    INDEX
    Explanations

    mentions of high-ranking individuals or people of authority

    oai_token-act-pair · gpt-3.5-turbo

    mentions of notable individuals or their titles

    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
    ageddon
    -0.78
    metry
    -0.74
    Characters
    -0.74
    hm
    -0.72
    RAFT
    -0.70
     qualifies
    -0.70
    holes
    -0.69
    iew
    -0.69
    jar
    -0.68
    thood
    -0.68
    POSITIVE LOGITS
     oldest
    1.34
     longest
    1.32
     youngest
    1.32
     eldest
    1.25
     largest
    1.19
     founder
    1.19
     grandson
    1.13
     infamous
    1.13
     former
    1.12
     richest
    1.11
    Activations Density 0.101%

    No Known Activations