© 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. 9099
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific TV program or channel

    oai_token-act-pair · gpt-3.5-turbo

    references to sports centers

    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
    velength
    -0.80
    vell
    -0.69
    livious
    -0.68
    intestinal
    -0.67
    witz
    -0.65
     Remastered
    -0.64
    seys
    -0.64
     Murd
    -0.64
     plur
    -0.63
    ipolar
    -0.62
    POSITIVE LOGITS
    æ©
    0.81
    é¾įåĸļ士
    0.77
    ENG
    0.76
    OC
    0.71
     Wei
    0.67
     Sheikh
    0.66
    âĶĢ
    0.65
    Han
    0.65
    EMS
    0.65
     Niet
    0.64
    Activations Density 0.000%

    No Known Activations