© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 2497
    Prev
    Next
    INDEX
    Explanations

    violent and medical-related concepts, including blood, cancer, and darkness

    oai_token-act-pair · gpt-3.5-turbo

    references to violence and death

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elfth
    -0.69
    hander
    -0.67
    Dispatch
    -0.66
    oday
    -0.66
     Publication
    -0.66
     ASA
    -0.64
    ACTED
    -0.64
    encer
    -0.64
     Participant
    -0.63
    peer
    -0.62
    POSITIVE LOGITS
     feces
    0.81
     rubble
    0.80
    dylib
    0.78
     goodies
    0.74
     vomit
    0.74
    flo
    0.69
     indistinguishable
    0.69
     garbage
    0.68
     metaphors
    0.68
     unimaginable
    0.67
    Activations Density 0.409%

    No Known Activations