Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 18872
    Prev
    Next
    INDEX
    Explanations

    words related to service or serving

    oai_token-act-pair · gpt-3.5-turbo

    references to "ser" and "serpent" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Breaker
    -0.83
    Memory
    -0.82
     Allies
    -0.79
    INGTON
    -0.76
     Memory
    -0.75
     GOODMAN
    -0.72
     Secretary
    -0.71
     Solution
    -0.70
     Suite
    -0.68
     Arcade
    -0.67
    POSITIVE LOGITS
    iously
    1.06
    ials
    1.00
    ping
    0.88
    iatric
    0.88
    iculture
    0.87
    iple
    0.87
    ieties
    0.87
    iety
    0.83
    geant
    0.83
    bian
    0.83
    Activations Density 0.016%

    No Known Activations