© 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. 8-RES-JB
    11. 14211
    Prev
    Next
    INDEX
    Explanations

    requirements or conditions that need to be met

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey requirements or conditions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    blogspot
    -0.76
    Written
    -0.75
    cycl
    -0.71
    cloth
    -0.69
    TL
    -0.67
    ient
    -0.59
    kin
    -0.59
    LESS
    -0.59
    option
    -0.58
    ahime
    -0.58
    POSITIVE LOGITS
     qualify
    1.29
     survive
    1.11
     justify
    1.09
     achieve
    1.06
     satisfy
    1.00
     ensure
    0.94
     overcome
    0.94
     constitute
    0.94
     guarantee
    0.92
     succeed
    0.91
    Activations Density 0.275%

    No Known Activations