© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 10203
    Prev
    Next
    INDEX
    Explanations

    information related to individuals named "Mel"

    oai_token-act-pair · gpt-3.5-turbo

    references to Mel or related individuals

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    æĸ¹
    -0.68
     Citizen
    -0.65
     Presidential
    -0.64
     Rage
    -0.64
     redress
    -0.63
    DragonMagazine
    -0.63
     altogether
    -0.60
     rigid
    -0.58
    ribute
    -0.58
    Quotes
    -0.58
    POSITIVE LOGITS
    atonin
    1.42
    inda
    1.30
    endez
    1.22
    bourne
    1.21
    odic
    1.11
    anch
    1.04
    odies
    1.00
    issa
    0.99
    ita
    0.98
    anches
    0.97
    Activations Density 0.027%

    No Known Activations