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. 22085
    Prev
    Next
    INDEX
    Explanations

    words related to physical discomfort or distress

    oai_token-act-pair · gpt-3.5-turbo

    gerunds or present participles in the text

    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
    bal
    -0.72
    omet
    -0.63
    onso
    -0.63
     rgb
    -0.62
    isible
    -0.62
    ŀ
    -0.62
    Neg
    -0.59
     Aerospace
    -0.59
    saf
    -0.58
    §
    -0.58
    POSITIVE LOGITS
     havoc
    0.89
    tons
    0.88
    redients
    0.88
    ulate
    0.83
    river
    0.74
    itcher
    0.72
    bilt
    0.72
     noises
    0.70
     Squid
    0.69
    stocks
    0.69
    Activations Density 0.125%

    No Known Activations