© 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. 10-RES-JB
    11. 18771
    Prev
    Next
    INDEX
    Explanations

    nouns related to reversals or changes in decisions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "rec" in various forms, indicating a focus on references to recording, recounting, or similar themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MENT
    -0.63
     Heidi
    -0.60
    NESS
    -0.59
     Masters
    -0.58
     Gren
    -0.58
     proprietary
    -0.57
     Gemini
    -0.56
     Cruiser
    -0.56
    AGES
    -0.56
     Nest
    -0.55
    POSITIVE LOGITS
    ategor
    1.26
    ourses
    1.24
    reating
    1.21
    urrence
    1.20
    usal
    1.18
    ieving
    1.16
    ieved
    1.14
    ursion
    1.10
    eding
    1.10
    ipient
    1.07
    Activations Density 0.009%

    No Known Activations