© 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. 0-RES-JB
    11. 22429
    Prev
    Next
    INDEX
    Explanations

    instances where satisfaction is expressed or implied

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to satisfaction and dissatisfaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olan
    -0.81
    age
    -0.75
    ade
    -0.69
     Attacks
    -0.67
     Throw
    -0.65
     Torch
    -0.64
    ansk
    -0.64
    kid
    -0.60
    ker
    -0.60
    ansom
    -0.59
    POSITIVE LOGITS
     satisfied
    3.94
     dissatisfied
    2.03
     Satisf
    1.99
     pleased
    1.81
     satisfaction
    1.80
     fulfilled
    1.76
     satisfy
    1.76
    atisf
    1.69
     satisfies
    1.63
     unsatisf
    1.58
    Activations Density 0.018%

    No Known Activations