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. 5985
    Prev
    Next
    INDEX
    Explanations

    concepts related to interpersonal relationships involving exploitation or taking advantage of others

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "others" in various contexts

    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
    ardo
    -0.63
     Dragonbound
    -0.59
    house
    -0.57
    Between
    -0.57
     Issue
    -0.57
     Between
    -0.55
    iform
    -0.55
    ization
    -0.55
    buster
    -0.54
    tick
    -0.54
    POSITIVE LOGITS
     others
    3.64
     Others
    2.77
    Others
    2.18
     other
    1.72
    other
    1.51
     elsewhere
    1.28
     rest
    1.25
     OTHER
    1.20
     Other
    1.14
    Other
    1.11
    Activations Density 0.027%

    No Known Activations