© 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. 9-RES-JB
    11. 19455
    Prev
    Next
    INDEX
    Explanations

    references to contrasting elements such as darkness and light

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to duality and contrast in experiences or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •shakespeare
    poetic contrast!

    No Comments

    Negative Logits
    related
    -0.77
    entially
    -0.76
    Overall
    -0.75
    Basically
    -0.74
    umably
    -0.74
     basically
    -0.72
    RM
    -0.71
    roup
    -0.70
    Newsletter
    -0.70
    Photo
    -0.70
    POSITIVE LOGITS
     glory
    1.23
     darkness
    1.22
     souls
    1.20
     majesty
    1.09
     eternal
    1.08
     righteousness
    1.08
     conquer
    1.07
     everlasting
    1.06
     ashes
    1.06
     gods
    1.06
    Activations Density 1.575%

    No Known Activations