© 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. 2947
    Prev
    Next
    INDEX
    Explanations

    academic institutions

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

    references to specific colleges or academic institutions

    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
     judging
    -0.73
     retract
    -0.70
    VALUE
    -0.68
    AGES
    -0.65
     injunction
    -0.62
     judges
    -0.60
     awarding
    -0.60
     proof
    -0.60
     derog
    -0.59
    YL
    -0.59
    POSITIVE LOGITS
    ombo
    1.45
    ossal
    1.38
    leen
    1.16
    fax
    1.14
    umbo
    1.14
    chester
    1.11
    ophon
    1.10
    angelo
    1.07
    ombie
    1.04
    lette
    1.04
    Activations Density 0.017%

    No Known Activations