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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 18368
    Prev
    Next
    INDEX
    Explanations

    words related to emphasizing something or standing out

    oai_token-act-pair · gpt-3.5-turbo

    references to inclusive language and collective terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ord
    -0.77
    roman
    -0.74
    perties
    -0.73
    angel
    -0.71
    odore
    -0.70
    opol
    -0.69
    adem
    -0.69
     Murdoch
    -0.68
    kr
    -0.67
    ãĥĥãĥĪ
    -0.67
    POSITIVE LOGITS
    THING
    1.10
    FORE
    1.08
     FUCK
    1.08
     THERE
    1.04
     MUCH
    1.02
    ISM
    1.00
     FANTASY
    0.99
    VER
    0.99
    FORM
    0.98
     RUN
    0.98
    Activations Density 0.171%

    No Known Activations