© 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. 3-RES-JB
    11. 10755
    Prev
    Next
    INDEX
    Explanations

    words related to moral judgment, often focusing on negative aspects such as immorality and irresponsibility

    oai_token-act-pair · gpt-3.5-turbo

    terms related to moral judgment and irresponsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erville
    -0.76
    inder
    -0.75
    aina
    -0.74
    ppa
    -0.72
    achine
    -0.67
    opa
    -0.67
    estone
    -0.66
    adal
    -0.65
    adders
    -0.64
    glas
    -0.64
    POSITIVE LOGITS
     wasteful
    0.80
     undermin
    0.76
     folly
    0.74
     foolish
    0.73
     irresponsible
    0.70
     perverse
    0.70
     indisc
    0.68
     aber
    0.68
     hypocritical
    0.66
     selfish
    0.66
    Activations Density 0.024%

    No Known Activations