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. 11949
    Prev
    Next
    INDEX
    Explanations

    signs or indications of various contexts or situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating signs of progress or change

    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
     Arena
    -0.67
     pores
    -0.64
     cabinets
    -0.64
    boro
    -0.64
    ken
    -0.62
    rients
    -0.62
    uge
    -0.61
    ggle
    -0.61
    FFER
    -0.61
    bers
    -0.60
    POSITIVE LOGITS
     customary
    0.72
     precaution
    0.71
     tradition
    0.70
     [|
    0.64
     derog
    0.64
    onymous
    0.62
     Cyrus
    0.61
     Shutdown
    0.60
     Hipp
    0.59
     srfAttach
    0.59
    Activations Density 0.504%

    No Known Activations