© 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. 24409
    Prev
    Next
    INDEX
    Explanations

    phrases prompting for feedback or opinions

    oai_token-act-pair · gpt-3.5-turbo

    queries or requests for opinions

    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
    arget
    -0.66
     Responsibility
    -0.62
    å§
    -0.61
     LIM
    -0.58
    abad
    -0.57
    church
    -0.57
     harms
    -0.56
     Prevention
    -0.55
     Fundamental
    -0.55
     Skydragon
    -0.54
    POSITIVE LOGITS
     wrought
    0.74
     fuss
    0.74
     entail
    0.69
    esan
    0.68
    esa
    0.68
    OOK
    0.66
     SAY
    0.64
    eka
    0.63
    atto
    0.63
    asta
    0.61
    Activations Density 0.136%

    No Known Activations