© 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. 7-RES-JB
    11. 1724
    Prev
    Next
    INDEX
    Explanations

    phrases related to career guidance or advice

    oai_token-act-pair · gpt-3.5-turbo

    conclusions and statements marked by punctuation such as periods and question marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     withdrawn
    -0.72
     haul
    -0.71
     withdraw
    -0.69
     tomb
    -0.68
     convoy
    -0.68
     disembark
    -0.68
     pocket
    -0.67
     inactive
    -0.67
    ributes
    -0.66
    belt
    -0.66
    POSITIVE LOGITS
     Fortunately
    1.27
     Luckily
    1.23
     Especially
    1.22
     Thankfully
    1.20
     Specifically
    1.19
     Ultimately
    1.19
     Particularly
    1.14
     Understanding
    1.14
     Whereas
    1.13
     Ideally
    1.12
    Activations Density 0.525%

    No Known Activations