© 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. 10-RES-JB
    11. 10608
    Prev
    Next
    INDEX
    Explanations

    specific instances or scenarios in a given context

    oai_token-act-pair · gpt-3.5-turbo

    references to specific "cases" or examples within a discussion

    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
    kefeller
    -0.82
    ongyang
    -0.71
    apult
    -0.66
    osponsors
    -0.65
     carbohyd
    -0.63
    ¥ŀ
    -0.62
    ailability
    -0.61
    arching
    -0.61
    arag
    -0.61
     newcom
    -0.61
    POSITIVE LOGITS
    ,
    0.82
    ,,
    0.64
    mma
    0.63
    >>>>>>>>
    0.63
     involving
    0.62
     anyways
    0.61
    forth
    0.61
     anyway
    0.61
    ,.
    0.60
     though
    0.60
    Activations Density 0.044%

    No Known Activations