© 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. 9898
    Prev
    Next
    INDEX
    Explanations

    phrases related to uniformity and conformity

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to conformity and societal expectations

    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
     recons
    -0.64
    ridor
    -0.63
     indeed
    -0.62
    berus
    -0.61
    alde
    -0.61
    cedented
    -0.60
    ESE
    -0.60
     conclud
    -0.60
    imar
    -0.59
    rieve
    -0.59
    POSITIVE LOGITS
     shitty
    1.22
     crappy
    1.17
     crap
    1.08
     mediocre
    1.00
     shit
    0.97
     boring
    0.88
     guy
    0.87
     fucking
    0.86
     paycheck
    0.85
     bullshit
    0.84
    Activations Density 0.791%

    No Known Activations