© 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. 10-RES-JB
    11. 20653
    Prev
    Next
    INDEX
    Explanations

    references to locations or positions of authority and power

    oai_token-act-pair · gpt-3.5-turbo

    terms related to authority and institutional structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     photographer
    -0.76
     spirited
    -0.72
     Rabbit
    -0.68
     magician
    -0.67
     loving
    -0.67
     rapist
    -0.66
     Photographer
    -0.65
     captive
    -0.64
     seeker
    -0.63
     lover
    -0.63
    POSITIVE LOGITS
    ices
    1.28
    acies
    1.28
    ories
    1.25
    ences
    1.24
    itures
    1.22
    ments
    1.21
    ancies
    1.21
    ements
    1.21
    ieties
    1.20
    uries
    1.17
    Activations Density 0.191%

    No Known Activations