© 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. 14906
    Prev
    Next
    INDEX
    Explanations

    comparisons of different qualities or attributes

    oai_token-act-pair · gpt-3.5-turbo

    comparative and superlative constructions

    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
    endiary
    -0.83
    iHUD
    -0.82
    ancial
    -0.71
    ctive
    -0.71
    sonian
    -0.70
    its
    -0.68
    UCT
    -0.67
    artifacts
    -0.67
    Constructed
    -0.65
    ciplinary
    -0.64
    POSITIVE LOGITS
     anybody
    1.18
     usual
    1.10
     anyone
    1.07
     everybody
    1.00
     everyone
    0.97
     others
    0.97
     yours
    0.91
     me
    0.88
     ours
    0.84
     us
    0.83
    Activations Density 0.162%

    No Known Activations