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. 0-RES-JB
    6. 21268
    Prev
    Next
    INDEX
    Explanations

    the name "kins" within a variety of contexts

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to individuals or names in the context of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Destination
    -0.68
     quantum
    -0.67
     void
    -0.67
     transmission
    -0.66
     recording
    -0.66
     Private
    -0.65
     vacuum
    -0.61
     PM
    -0.61
     aircraft
    -0.60
     trace
    -0.60
    POSITIVE LOGITS
    kins
    4.92
    kin
    2.92
    kinson
    2.26
    kens
    1.51
    kes
    1.44
    kson
    1.18
    hens
    1.16
    kas
    1.15
    kers
    1.15
    kos
    1.15
    Activations Density 0.010%

    No Known Activations