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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 15094
    Prev
    Next
    INDEX
    Explanations

    phrases related to one-on-one interactions or personal attention

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "on" and its contextual use in phrases

    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
    aido
    -0.75
    SPONSORED
    -0.73
     Rena
    -0.73
    اÙĦ
    -0.66
    hower
    -0.64
    ulkan
    -0.60
    gans
    -0.60
    kamp
    -0.59
    Kings
    -0.59
     Referred
    -0.58
    POSITIVE LOGITS
    lihood
    0.81
    opsis
    0.78
    iversal
    0.76
    cation
    0.75
    etheless
    0.74
    ousand
    0.73
    thood
    0.73
    ounce
    0.72
    clusive
    0.69
    usterity
    0.69
    Activations Density 0.065%

    No Known Activations