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. 9-RES-JB
    6. 8264
    Prev
    Next
    INDEX
    Explanations

    terms related to family relationships and personal details

    oai_token-act-pair · gpt-3.5-turbo

    familial relationships and age references

    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
     guiName
    -0.82
     themselves
    -0.80
     ourselves
    -0.79
     itself
    -0.76
     oneself
    -0.72
     Vend
    -0.68
     Rohing
    -0.68
     yourselves
    -0.67
     Turks
    -0.66
     Meadows
    -0.66
    POSITIVE LOGITS
    favorite
    1.21
     counterparts
    1.11
    own
    1.03
     brethren
    1.01
     selves
    1.00
    friends
    0.97
     mates
    0.96
    mates
    0.96
     buddies
    0.95
    mate
    0.95
    Activations Density 0.509%

    No Known Activations