© 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. 2-RES-JB
    11. 21967
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or conventions, particularly Comic-Con

    oai_token-act-pair · gpt-3.5-turbo

    references to comic conventions

    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
     destro
    -0.66
    terday
    -0.65
    =[
    -0.63
    ...]
    -0.61
     hydra
    -0.60
    ĪĴ
    -0.60
     aval
    -0.60
    é»Ĵ
    -0.59
     Penalty
    -0.59
     practicable
    -0.59
    POSITIVE LOGITS
    stant
    0.93
    nex
    0.91
    Con
    0.88
    ECA
    0.86
    naissance
    0.82
    atur
    0.81
    clusions
    0.80
    ference
    0.79
    ventions
    0.79
     Convention
    0.77
    Activations Density 0.008%

    No Known Activations