© 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. 7-RES-JB
    11. 23940
    Prev
    Next
    INDEX
    Explanations

    scientific or technical terms

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to cognitive and emotional processes in humor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cour
    -0.84
     trailer
    -0.75
    lance
    -0.74
     reel
    -0.74
     Trailer
    -0.73
     Throne
    -0.71
    ilet
    -0.71
     Ike
    -0.70
     Journalism
    -0.70
    udeb
    -0.70
    POSITIVE LOGITS
     biologically
    1.29
     causal
    1.13
     microbial
    1.11
     endogenous
    1.11
     phenotype
    1.11
     âĪ¼
    1.11
     adaptive
    1.09
     detectable
    1.08
     susceptibility
    1.07
     evolutionary
    1.06
    Activations Density 0.815%

    No Known Activations