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

    Neuronpedia

    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. 2-RES-JB
    11. 17650
    Prev
    Next
    INDEX
    Explanations

    the word "bot" with varying degrees of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    references to artificial intelligence or robotic entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    journal
    -0.71
     Difference
    -0.65
    egal
    -0.63
    uncture
    -0.60
     Koen
    -0.60
    UME
    -0.59
     ACTION
    -0.59
     Situation
    -0.58
     Scheme
    -0.58
    eways
    -0.58
    POSITIVE LOGITS
    anical
    1.16
    anooga
    1.02
    cham
    1.01
    anic
    0.97
    bot
    0.90
    opia
    0.90
    olean
    0.90
    ertodd
    0.89
    ãĤ´ãĥ³
    0.89
    ically
    0.88
    Activations Density 0.006%

    No Known Activations