© 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. 11-RES-JB
    11. 12443
    Prev
    Next
    INDEX
    Explanations

    names or variations of the name "Er"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of a specific name or title related to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    esses
    -0.66
     debut
    -0.63
     sight
    -0.63
     climax
    -0.62
    ãģ®éŃĶ
    -0.59
    sites
    -0.59
     CONTIN
    -0.59
     Array
    -0.59
     relentlessly
    -0.58
     containment
    -0.57
    POSITIVE LOGITS
    lang
    1.17
    asure
    1.14
    rors
    1.13
    asm
    1.08
    nie
    1.08
    win
    1.05
    bil
    1.05
    lich
    1.01
    aser
    1.01
    tz
    1.00
    Activations Density 0.018%

    No Known Activations