© 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. 11-RES-JB
    11. 14844
    Prev
    Next
    INDEX
    Explanations

    references to negative situations or issues, such as injuries, diseases, accidents, and difficulties

    oai_token-act-pair · gpt-3.5-turbo

    concerns related to animal welfare and societal issues

    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
    oday
    -0.72
    !]
    -0.66
     HERE
    -0.64
    uador
    -0.62
     *)
    -0.62
    ashtra
    -0.61
    "]
    -0.60
     ];
    -0.59
    MpServer
    -0.58
    ]"
    -0.58
    POSITIVE LOGITS
     undet
    0.88
     alike
    0.88
     unseen
    0.81
     unheard
    0.80
     unless
    0.79
     regardless
    0.78
     unmatched
    0.77
     rarely
    0.76
    often
    0.75
     seldom
    0.75
    Activations Density 0.711%

    No Known Activations