© 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. 11-RES-JB
    11. 10171
    Prev
    Next
    INDEX
    Explanations

    phrases related to sacrifice and risking lives

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to sacrifice and loss of life

    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
    etsk
    -0.66
    ensional
    -0.63
    Orig
    -0.60
    ailability
    -0.59
    yrinth
    -0.59
    urated
    -0.58
     ausp
    -0.58
    ateur
    -0.57
    ilyn
    -0.54
    farious
    -0.53
    POSITIVE LOGITS
     unnecessarily
    1.00
     trying
    0.91
     for
    0.90
     hoping
    0.84
     figuring
    0.82
     sacrificing
    0.82
     risking
    0.81
     buying
    0.80
     to
    0.77
     searching
    0.77
    Activations Density 0.330%

    No Known Activations