© 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 EvalsExportsinterp-engineNEWAPI 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. 24510
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions that can be done without any consequences or repercussions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating actions that occur without external interference or oversight

    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
    raq
    -0.87
    late
    -0.77
    mun
    -0.76
    iers
    -0.75
    cow
    -0.71
    geist
    -0.71
    lish
    -0.68
    mers
    -0.66
     Presence
    -0.65
    =-=-=-=-=-=-=-=-
    -0.64
    POSITIVE LOGITS
     sacrificing
    1.14
     regard
    1.05
     mentioning
    1.04
     necessarily
    1.04
     compromising
    1.02
     risking
    1.02
     hesitation
    1.00
     knowing
    0.98
     relying
    0.97
     requiring
    0.96
    Activations Density 0.046%

    No Known Activations