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. 6166
    Prev
    Next
    INDEX
    Explanations

    ancient Greek or mythical references

    oai_token-act-pair · gpt-3.5-turbo

    references to specific characters or entities in a fictional or narrative context

    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
    ï¸ı
    -0.72
    soDeliveryDate
    -0.71
    Downloadha
    -0.71
    earable
    -0.69
    RANT
    -0.69
    alore
    -0.66
    UGC
    -0.65
    olicy
    -0.64
     COURT
    -0.64
    twitch
    -0.63
    POSITIVE LOGITS
    ukong
    0.65
    orld
    0.63
     Gry
    0.62
     Humanity
    0.62
    adesh
    0.61
    obos
    0.61
     Gibbs
    0.61
    aters
    0.61
     McAuliffe
    0.60
    iors
    0.60
    Activations Density 0.241%

    No Known Activations