© 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. 10326
    Prev
    Next
    INDEX
    Explanations

    the name "Mic" with varying levels of specificity (given by different activation values)

    oai_token-act-pair · gpt-3.5-turbo

    references to the character "Mic" in various contexts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ACTED
    -0.72
     Unified
    -0.71
     Dull
    -0.67
    IVES
    -0.64
    ENGTH
    -0.63
     ANGEL
    -0.60
     Spit
    -0.60
    ãĤĤ
    -0.59
    OUGH
    -0.58
    tenance
    -0.58
    POSITIVE LOGITS
    roman
    1.28
    ropolitan
    1.27
    HAEL
    1.22
    helle
    1.21
    rones
    1.15
    illin
    1.06
    rom
    1.05
    onductor
    1.04
    olon
    1.03
    ron
    1.03
    Activations Density 0.050%

    No Known Activations