© 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. 9-RES-JB
    11. 17933
    Prev
    Next
    INDEX
    Explanations

    quotes or statements emphasizing moral principles and values

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to morality and ethical considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.83
    vernment
    -0.75
    oops
    -0.69
    OULD
    -0.69
    arger
    -0.68
    arnaev
    -0.67
    ANS
    -0.67
    ORTS
    -0.67
    iliar
    -0.66
    aido
    -0.64
    POSITIVE LOGITS
     motiv
    1.00
     criterion
    0.95
     noun
    0.91
     predictor
    0.90
     motive
    0.86
     ingredient
    0.84
     prerequisite
    0.84
     determin
    0.83
     currency
    0.82
    iator
    0.82
    Activations Density 0.400%

    No Known Activations