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. 18810
    Prev
    Next
    INDEX
    Explanations

    words related to strength, effectiveness, and reliable performance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "robust" and its variations, indicating a focus on strength and resilience 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
    pper
    -0.65
    Station
    -0.63
     clicked
    -0.62
     Fever
    -0.62
     Khe
    -0.62
     Suc
    -0.61
    hops
    -0.60
     Station
    -0.60
    Companies
    -0.59
    avez
    -0.59
    POSITIVE LOGITS
    ly
    1.15
    ness
    1.07
    ively
    0.99
    nesses
    0.98
    mble
    0.91
    ament
    0.87
    ity
    0.85
    itude
    0.85
    atility
    0.84
    edly
    0.83
    Activations Density 0.014%

    No Known Activations