© 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. 10-RES-JB
    11. 17266
    Prev
    Next
    INDEX
    Explanations

    words related to expectations and societal norms

    oai_token-act-pair · gpt-3.5-turbo

    phrases and forms of expression related to expectations and obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    confirmed
    -0.73
     concluding
    -0.72
     millenn
    -0.69
    DAQ
    -0.69
    roads
    -0.69
    binding
    -0.68
    quickShipAvailable
    -0.68
     confirming
    -0.67
     è£ıè¦ļéĨĴ
    -0.66
    era
    -0.66
    POSITIVE LOGITS
     behave
    1.59
     obey
    1.43
     adhere
    1.19
     strive
    1.16
     conform
    1.16
     eat
    1.16
     tolerate
    1.15
     wear
    1.13
     spend
    1.13
     earn
    1.13
    Activations Density 0.363%

    No Known Activations