© 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. 2778
    Prev
    Next
    INDEX
    Explanations

    phrases related to social and political commentary

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

    references to direct comparisons or similarities between characters and concepts

    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
    flush
    -0.69
     busy
    -0.68
    wm
    -0.66
     Topics
    -0.66
    nels
    -0.65
     stalls
    -0.64
    otions
    -0.63
     wastes
    -0.62
    issues
    -0.61
    affer
    -0.61
    POSITIVE LOGITS
     resemb
    1.62
     resemblance
    1.52
     parallels
    1.41
     similarity
    1.34
     similarities
    1.33
     imitation
    1.32
     homage
    1.31
     likeness
    1.23
     analogous
    1.21
    imilar
    1.21
    Activations Density 0.569%

    No Known Activations