© 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. 8-RES-JB
    11. 2701
    Prev
    Next
    INDEX
    Explanations

    phrases related to enjoyment or experiencing positive emotions

    oai_token-act-pair · gpt-3.5-turbo

    instances of enjoyment or positive experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -1.07
    RFC
    -0.74
    nton
    -0.68
    vernment
    -0.67
    osponsors
    -0.65
     coordin
    -0.63
     Willis
    -0.62
     Debor
    -0.62
     eyebrow
    -0.62
     Carney
    -0.61
    POSITIVE LOGITS
     pleasures
    1.01
     leisure
    1.00
     enjoyment
    0.98
     fullest
    0.86
     fruits
    0.85
     festivities
    0.82
     hospitality
    0.80
     thrill
    0.80
     freedoms
    0.79
     freedom
    0.78
    Activations Density 0.170%

    No Known Activations