© 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 EvalsExportsinterp-engineNEWAPI 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. 5647
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a broader or deeper significance beyond initial appearances

    oai_token-act-pair · gpt-3.5-turbo

    assertions that emphasize something is more than just one aspect or factor

    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
     respectively
    -0.81
    acker
    -0.75
    azar
    -0.72
     srfAttach
    -0.71
    rather
    -0.70
     ALSO
    -0.66
     earliest
    -0.64
    iblings
    -0.63
    bis
    -0.63
     PLUS
    -0.63
    POSITIVE LOGITS
    ifiable
    1.30
     anymore
    0.91
    ifications
    0.81
     passively
    0.78
     anybody
    0.72
     coincidence
    0.72
     another
    0.71
     about
    0.71
     anecd
    0.69
     blindly
    0.69
    Activations Density 0.079%

    No Known Activations