© 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. 6-RES-JB
    11. 7935
    Prev
    Next
    INDEX
    Explanations

    superlatives related to comedic or absurd elements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to humor and absurdity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Maid
    -0.77
     arms
    -0.63
     vows
    -0.61
     healthcare
    -0.61
     Spear
    -0.61
     Shepherd
    -0.61
     tract
    -0.61
     telecom
    -0.60
     Knights
    -0.60
     GEAR
    -0.60
    POSITIVE LOGITS
    iest
    1.49
    iness
    1.42
    eless
    1.34
    eness
    1.22
    ily
    1.19
    ier
    1.18
    ibility
    1.15
    etr
    1.15
    orship
    1.11
    efully
    1.09
    Activations Density 0.051%

    No Known Activations