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. 6901
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "Us" with a high focus on the number "9"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of "Us," indicating a focus on collective identity or community

    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
     whip
    -0.69
    hearted
    -0.66
    nered
    -0.66
     limp
    -0.64
     hindsight
    -0.64
     raise
    -0.64
     reflection
    -0.64
     KEY
    -0.61
     ministerial
    -0.61
     jump
    -0.60
    POSITIVE LOGITS
    Us
    4.44
    U
    1.55
     Us
    1.48
    Os
    1.21
    Es
    1.19
    Vs
    1.14
    Ut
    1.09
    Ps
    1.09
    Gs
    1.08
    Me
    1.07
    Activations Density 0.012%

    No Known Activations