© 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. 3580
    Prev
    Next
    INDEX
    Explanations

    terms related to origins, historical facts, and notable occurrences

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

    the term "orig" in various forms, indicating a focus on the concept of origin or originality

    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
     wedge
    -0.64
    farm
    -0.64
    fall
    -0.64
     dotted
    -0.60
     hearing
    -0.59
     ox
    -0.59
     subdiv
    -0.58
     chau
    -0.57
     fracture
    -0.57
     flu
    -0.56
    POSITIVE LOGITS
    inals
    1.44
    inating
    1.36
    inated
    1.30
    inally
    1.27
    ami
    1.25
    INAL
    1.24
    inates
    1.15
    ination
    1.09
    inations
    1.00
    rative
    0.99
    Activations Density 0.038%

    No Known Activations