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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 2768
    Prev
    Next
    INDEX
    Explanations

    onomatopoeic words and sounds

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to surprise or unexpected reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MFT
    -0.74
     segregated
    -0.69
    ãĤ¤ãĥĪ
    -0.69
     successors
    -0.68
     outsourcing
    -0.68
     restrictions
    -0.66
     specialization
    -0.66
     segreg
    -0.66
    abase
    -0.65
     Architects
    -0.65
    POSITIVE LOGITS
     laughter
    1.32
     coughing
    1.25
     laugh
    1.22
     chuckle
    1.21
     grin
    1.17
     moan
    1.16
     gasp
    1.14
    laugh
    1.13
     noises
    1.12
     cough
    1.10
    Activations Density 0.269%

    No Known Activations