© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 1014
    Prev
    Next
    INDEX
    Explanations

    verbs related to questioning or pushing back on established ideas

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "challenge" and its variations, indicating discussions about contesting ideas or authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abet
    -0.81
    ng
    -0.71
    ufact
    -0.68
    ]}
    -0.66
    ther
    -0.66
    ops
    -0.65
    ··
    -0.65
    agh
    -0.64
    oped
    -0.62
    holm
    -0.61
    POSITIVE LOGITS
     assumptions
    1.15
     stereotypes
    1.12
     precon
    1.07
     orthodoxy
    0.97
     misconceptions
    0.96
     perceptions
    0.94
     beliefs
    0.93
     myths
    0.88
     belief
    0.83
     assertions
    0.82
    Activations Density 0.168%

    No Known Activations