© 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. 17696
    Prev
    Next
    INDEX
    Explanations

    mentions and descriptions of various people, places, and actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "even" and highlight its repetitive use in various contexts

    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
    along
    -0.73
    qqa
    -0.73
    essa
    -0.67
    null
    -0.63
    module
    -0.61
    town
    -0.59
    ijing
    -0.59
    oshenko
    -0.59
    ourse
    -0.59
    ————
    -0.59
    POSITIVE LOGITS
     Fran
    0.68
     Himself
    0.68
     jokes
    0.67
     mentioning
    0.66
     curs
    0.65
     admit
    0.65
    iffe
    0.64
     watered
    0.64
     concedes
    0.64
     concede
    0.63
    Activations Density 0.323%

    No Known Activations