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. 8510
    Prev
    Next
    INDEX
    Explanations

    references to specific bills or legislation

    oai_token-act-pair · gpt-3.5-turbo

    legislative references to specific bills or laws

    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
    istically
    -0.97
    pmwiki
    -0.79
     rall
    -0.75
    coni
    -0.67
    aneous
    -0.66
     Earthqu
    -0.65
    ========
    -0.64
    eele
    -0.63
     Capitals
    -0.62
    istics
    -0.61
    POSITIVE LOGITS
    Gary
    1.11
    HB
    0.99
    heit
    0.92
    KB
    0.91
    ¶ħ
    0.89
    ¿½
    0.80
    acking
    0.77
    iHUD
    0.77
    terness
    0.76
    azard
    0.76
    Activations Density 0.021%

    No Known Activations