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. 3115
    Prev
    Next
    INDEX
    Explanations

    something that happened on a specific day of the week in a particular location

    oai_token-act-pair · gpt-3.5-turbo

    references to specific nights of the week

    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
    cient
    -0.70
    UTF
    -0.69
    inter
    -0.65
    esp
    -0.64
    location
    -0.64
    annah
    -0.63
    atem
    -0.63
    ERY
    -0.61
    recated
    -0.61
    ignant
    -0.61
    POSITIVE LOGITS
    night
    0.82
     afternoon
    0.75
     night
    0.71
     onwards
    0.67
     evening
    0.65
    opers
    0.63
     UPDATE
    0.63
     onward
    0.63
    nesday
    0.62
    fall
    0.62
    Activations Density 0.034%

    No Known Activations