© 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. 12-RES-JB
    11. 2912
    Prev
    Next
    INDEX
    Explanations

    phrases related to relationships and decision-making

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases and contexts related to personal relationships and emotional struggles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Otherwise
    -0.74
    ?).
    -0.73
    ?ãĢį
    -0.70
    edi
    -0.70
    ?".
    -0.70
    ``
    -0.66
    ?),
    -0.65
    >]
    -0.64
    '?
    -0.64
     Your
    -0.63
    POSITIVE LOGITS
    ciating
    0.83
    mails
    0.82
     meetings
    0.80
     seminars
    0.79
     conferences
    0.78
     innumerable
    0.78
     countless
    0.78
     dinners
    0.77
     spor
    0.76
     tirelessly
    0.76
    Activations Density 0.793%

    No Known Activations