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. 11199
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a cryptocurrency called Vertcoin

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity or brand involving "Vert" or similar terms

    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
    aeda
    -0.82
    usha
    -0.69
    riages
    -0.67
    ramid
    -0.66
    pper
    -0.64
    orters
    -0.64
    negie
    -0.64
    crew
    -0.63
    ourke
    -0.62
     mash
    -0.62
    POSITIVE LOGITS
    ible
    1.10
    ically
    1.05
    ibility
    0.93
    icals
    0.93
    worthiness
    0.88
    ibly
    0.87
    ured
    0.83
    ical
    0.82
    emis
    0.80
    ures
    0.79
    Activations Density 0.057%

    No Known Activations