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. 21035
    Prev
    Next
    INDEX
    Explanations

    instances where something is being given a specific level of attention or consideration

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "give 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
    velt
    -0.67
    Connect
    -0.64
    nown
    -0.63
    Quantity
    -0.63
    iffe
    -0.61
    alde
    -0.58
    dayName
    -0.57
    enegger
    -0.57
    IX
    -0.57
    FIG
    -0.56
    POSITIVE LOGITS
     permission
    1.12
     precedence
    1.09
     priority
    1.05
     thumbs
    0.96
     pause
    0.86
     legitimacy
    0.85
     impetus
    0.82
     away
    0.82
     props
    0.81
     credibility
    0.80
    Activations Density 0.099%

    No Known Activations