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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-RES-JB
    6. 10640
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical confrontation or competition

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and their relationship to control and power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.64
     whistleblowers
    -0.61
    uge
    -0.60
     gladly
    -0.58
    very
    -0.57
     smarter
    -0.57
     underestimated
    -0.56
    huge
    -0.55
    soDeliveryDate
    -0.55
     experiences
    -0.54
    POSITIVE LOGITS
     theirs
    0.82
     ours
    0.67
     the
    0.67
     hostilities
    0.66
     his
    0.64
     hers
    0.63
     their
    0.63
     fruition
    0.62
    rium
    0.61
     Constantinople
    0.61
    Activations Density 0.708%

    No Known Activations