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. 8-RES-JB
    6. 21687
    Prev
    Next
    INDEX
    Explanations

    elderly individuals or characteristics associated with them

    oai_token-act-pair · gpt-3.5-turbo

    descriptive attributes related to different types of hair and age

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ô
    -0.87
    inventoryQuantity
    -0.86
    Tokens
    -0.80
    imum
    -0.78
    ieties
    -0.77
    irtual
    -0.76
    sbm
    -0.76
    issions
    -0.75
    tools
    -0.74
    uden
    -0.72
    POSITIVE LOGITS
     woman
    1.44
     lady
    1.27
     man
    1.27
     girl
    1.16
     gentleman
    1.14
     teenager
    1.12
     guy
    1.12
     boy
    1.11
     female
    1.11
     male
    1.10
    Activations Density 0.209%

    No Known Activations