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

    Neuronpedia

    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. 6418
    Prev
    Next
    INDEX
    Explanations

    terms related to negative or immoral behaviors

    oai_token-act-pair · gpt-3.5-turbo

    characteristics related to moral or ethical ambiguity

    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
     avenues
    -0.80
     inputs
    -0.80
     interfaces
    -0.80
     banks
    -0.80
     arcs
    -0.79
     intersections
    -0.77
     foundations
    -0.77
     bridges
    -0.74
     platforms
    -0.73
     positives
    -0.73
    POSITIVE LOGITS
    iddler
    1.13
    ibrarian
    1.13
    agonist
    1.12
    romancer
    1.10
    apper
    1.09
    ector
    1.07
    acker
    1.07
    former
    1.06
    utenant
    1.05
    olester
    1.04
    Activations Density 0.252%

    No Known Activations