© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 2592
    Prev
    Next
    INDEX
    Explanations

    profanity and negative expressions

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

    expressions of frustration or disappointment

    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
    Enlarge
    -0.90
    ":[
    -0.76
    isSpecialOrderable
    -0.72
    toggle
    -0.72
    \":
    -0.70
    Explore
    -0.66
    Newsletter
    -0.64
    ":[{"
    -0.64
    án
    -0.63
     explor
    -0.63
    POSITIVE LOGITS
     FUCK
    1.53
     shitty
    1.35
     fucking
    1.34
     goddamn
    1.28
     fucked
    1.18
     shit
    1.17
     fuckin
    1.16
     retarded
    1.15
     bullshit
    1.14
    shit
    1.13
    Activations Density 1.003%

    No Known Activations