© 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. 19971
    Prev
    Next
    INDEX
    Explanations

    phrases related to requirements or conditions that need to be met

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements related to success or requirements

    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
     Cosponsors
    -0.89
     Cutter
    -0.70
    ahime
    -0.68
     Boat
    -0.64
     boiler
    -0.63
    scripts
    -0.61
    LESS
    -0.61
    cloth
    -0.61
     pled
    -0.60
     Minute
    -0.60
    POSITIVE LOGITS
     succeed
    1.14
     prosper
    1.14
     thrive
    1.13
     survive
    1.13
     viable
    1.08
     effectively
    1.04
     success
    1.04
     truly
    1.03
     sustainable
    1.02
     viability
    1.01
    Activations Density 0.255%

    No Known Activations