© 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. 10-RES-JB
    11. 708
    Prev
    Next
    INDEX
    Explanations

    instances where something is emphasized or given importance

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the importance of something or someone in varying degrees

    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
     Observatory
    -0.69
     Anth
    -0.63
    Enter
    -0.59
     Ide
    -0.56
     archae
    -0.55
     Enter
    -0.55
     Ob
    -0.53
     optics
    -0.53
    APD
    -0.53
     surveys
    -0.53
    POSITIVE LOGITS
     lot
    1.48
     bit
    1.38
     LOT
    1.31
     little
    1.16
     tad
    1.16
    uras
    1.11
    rouse
    1.01
     heck
    0.98
    little
    0.96
     ton
    0.94
    Activations Density 0.153%

    No Known Activations