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. 10214
    Prev
    Next
    INDEX
    Explanations

    mentions of financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    instances of high-stakes decision-making or conflict

    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
     Trafford
    -0.58
    Loading
    -0.55
     Able
    -0.47
     Lumia
    -0.47
     derby
    -0.46
     Canary
    -0.46
     Mig
    -0.46
     Axel
    -0.46
     GHz
    -0.46
    Must
    -0.45
    POSITIVE LOGITS
    etheless
    0.91
    NetMessage
    0.57
    gregation
    0.55
    ç¥ŀ
    0.52
    76561
    0.51
    prison
    0.50
     respectively
    0.49
    iannopoulos
    0.48
    collect
    0.48
    çī
    0.48
    Activations Density 3.084%

    No Known Activations