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. 7938
    Prev
    Next
    INDEX
    Explanations

    time-related information such as dates, times, locations, and specific details in posts or profiles

    oai_token-act-pair · gpt-3.5-turbo

    timestamps and editing details in posts

    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
     pestic
    -0.77
    channelAvailability
    -0.72
     nuns
    -0.72
     missionaries
    -0.71
    fell
    -0.71
     Palestin
    -0.71
    senal
    -0.67
    gettable
    -0.67
     Episcopal
    -0.67
     Boko
    -0.66
    POSITIVE LOGITS
     Posts
    0.79
    ertodd
    0.78
     Edited
    0.71
    gres
    0.71
    azo
    0.70
     LW
    0.70
    Thread
    0.69
     gmaxwell
    0.68
    estamp
    0.68
    UTC
    0.67
    Activations Density 0.036%

    No Known Activations