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. 1661
    Prev
    Next
    INDEX
    Explanations

    paths or routes towards different outcomes or destinations

    oai_token-act-pair · gpt-3.5-turbo

    references to various metaphorical paths or courses of action in discussions

    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
    zona
    -0.80
     Hots
    -0.65
    ENCY
    -0.63
     Bots
    -0.63
     sterling
    -0.63
    orpor
    -0.61
    initions
    -0.60
     NOTICE
    -0.60
     Bundes
    -0.59
    rongh
    -0.59
    POSITIVE LOGITS
    finding
    1.18
    finder
    1.06
     paths
    1.03
    ways
    1.00
    ogen
    0.94
    find
    0.91
    ologies
    0.90
     path
    0.88
    way
    0.84
    breaking
    0.83
    Activations Density 0.025%

    No Known Activations