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. 18590
    Prev
    Next
    INDEX
    Explanations

    action verbs related to making changes or decisions

    oai_token-act-pair · gpt-3.5-turbo

    commands or suggestions for actions

    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
     guiActiveUnfocused
    -0.82
    Downloadha
    -0.76
     respectively
    -0.63
    ashington
    -0.56
    after
    -0.55
    luster
    -0.53
    Host
    -0.52
    >>\
    -0.52
    quartered
    -0.51
    BuyableInstoreAndOnline
    -0.50
    POSITIVE LOGITS
    ulate
    0.91
     ourselves
    0.86
     oneself
    0.84
     yourself
    0.80
     yourselves
    0.76
    uate
    0.76
    iate
    0.71
     somet
    0.70
     myself
    0.70
    ayne
    0.69
    Activations Density 0.645%

    No Known Activations