© 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. 3343
    Prev
    Next
    INDEX
    Explanations

    phrases related to future plans or intentions

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

    phrases related to predictions and forward-looking statements

    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
    .'
    -1.42
    ,'
    -1.40
    ?'
    -1.32
    !'
    -1.28
    '.
    -1.18
    ',
    -1.17
    )'
    -1.15
    âĢIJ
    -1.14
    ':
    -1.12
    ').
    -1.10
    POSITIVE LOGITS
     "
    1.58
     "-
    1.49
     "...
    1.43
     "[
    1.39
     "+
    1.38
     "'
    1.38
     "(
    1.37
     "_
    1.37
     "@
    1.34
     "#
    1.34
    Activations Density 0.392%

    No Known Activations