© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 21299
    Prev
    Next
    INDEX
    Explanations

    phrases related to moral or ethical expectations imposed on individuals by society or specific groups

    oai_token-act-pair · gpt-3.5-turbo

    mandates and moral imperatives related to behavior and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemTracker
    -0.75
    arthed
    -0.74
    interstitial
    -0.72
    hof
    -0.71
    igor
    -0.70
    ergus
    -0.65
    loading
    -0.64
    confirmed
    -0.63
    roads
    -0.63
    warming
    -0.63
    POSITIVE LOGITS
     behave
    1.44
     obey
    1.41
     conform
    1.36
     adhere
    1.29
     discriminate
    1.23
     strive
    1.17
     tolerate
    1.17
     abide
    1.16
     participate
    1.16
     violate
    1.14
    Activations Density 0.305%

    No Known Activations