© 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. 1-RES-JB
    11. 3333
    Prev
    Next
    INDEX
    Explanations

    words related to enjoyment, satisfaction, or positive experiences

    oai_token-act-pair · gpt-3.5-turbo

    expressions of pleasure in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pat
    -0.76
    é¾
    -0.74
    REE
    -0.74
    NR
    -0.63
    ept
    -0.63
    smart
    -0.62
    enz
    -0.61
    mt
    -0.61
     DOT
    -0.61
     dotted
    -0.61
    POSITIVE LOGITS
     pleasure
    1.52
     gratification
    1.10
     pleasures
    1.00
     enjoyment
    0.96
    obbies
    0.92
     pleas
    0.91
     thrill
    0.87
    retion
    0.86
    urous
    0.83
     curiosity
    0.81
    Activations Density 0.005%

    No Known Activations