© 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 EvalsExportsAPI 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. 7463
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate an addition or enhancement to something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "add" and its variations related to contribution or accumulation

    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
    eve
    -0.63
    Released
    -0.63
    prototype
    -0.63
    doi
    -0.59
    sites
    -0.59
    zee
    -0.58
    kay
    -0.58
    bis
    -0.57
    ck
    -0.57
    kat
    -0.56
    POSITIVE LOGITS
     insult
    1.27
     urgency
    1.07
    endum
    1.05
     impetus
    1.03
    ictions
    1.03
     fuel
    1.00
     dimension
    0.93
     complexity
    0.92
     depth
    0.91
     legitimacy
    0.91
    Activations Density 0.060%

    No Known Activations