© 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. 16209
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to tragic events or crises

    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
     vibrations
    -0.56
     glitches
    -0.55
     ventilation
    -0.55
    getic
    -0.54
     scaven
    -0.51
     vomiting
    -0.51
     exch
    -0.50
     cryptographic
    -0.50
     adhesive
    -0.50
     parachute
    -0.50
    POSITIVE LOGITS
    ©¶æ
    0.64
    ¶
    0.62
    oubtedly
    0.58
    etheless
    0.57
     lately
    0.57
     ostensibly
    0.56
    today
    0.56
     ours
    0.55
    uably
    0.54
     Nationals
    0.54
    Activations Density 1.222%

    No Known Activations