© 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. 2-RES-JB
    11. 17090
    Prev
    Next
    INDEX
    Explanations

    terms related to societal issues and concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to societal issues and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urations
    -0.97
    word
    -0.91
    Pad
    -0.75
    etsk
    -0.71
    è¦ļéĨĴ
    -0.68
    Word
    -0.66
    term
    -0.66
    gotten
    -0.66
    ifer
    -0.66
    sbm
    -0.65
    POSITIVE LOGITS
     society
    0.86
    anguage
    0.80
     Royale
    0.74
    eers
    0.72
     Society
    0.71
    ically
    0.71
    fare
    0.70
    wide
    0.70
    liness
    0.69
     acad
    0.68
    Activations Density 0.017%

    No Known Activations