© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 15204
    Prev
    Next
    INDEX
    Explanations

    strong emotional reactions or opinions expressed in text

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to negative actions or complaints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nai
    -0.68
     Bei
    -0.64
     Bonds
    -0.64
    peria
    -0.63
    Asia
    -0.63
    ortium
    -0.63
    é¾įå
    -0.63
     Suc
    -0.61
     Timeline
    -0.60
    WIN
    -0.58
    POSITIVE LOGITS
    essional
    0.75
    igious
    0.75
    untled
    0.75
    backer
    0.71
    sed
    0.69
    kefeller
    0.68
    quit
    0.66
    anks
    0.64
    rolled
    0.64
    Edited
    0.64
    Activations Density 0.039%

    No Known Activations