Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 4307
    Prev
    Next
    INDEX
    Explanations

    phrases conveying reassurance or comfort in the face of difficult situations

    oai_token-act-pair · gpt-3.5-turbo

    the word 'it' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dayton
    -0.63
     Eighth
    -0.62
    Reviewer
    -0.61
     Adjusted
    -0.56
    dding
    -0.55
     multip
    -0.54
     Polk
    -0.54
     Recon
    -0.53
    VIEW
    -0.53
     mindful
    -0.53
    POSITIVE LOGITS
     hurts
    1.39
     ain
    1.31
     happens
    1.25
    alian
    1.24
     sucks
    1.22
     doesnt
    1.21
    chy
    1.19
     seems
    1.15
     depends
    1.14
    unes
    1.12
    Activations Density 0.259%

    No Known Activations