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. 8705
    Prev
    Next
    INDEX
    Explanations

    adjectives or verbs related to criticism or complacency

    oai_token-act-pair · gpt-3.5-turbo

    terms related to complaints or grievances

    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
    hyde
    -0.90
    bucks
    -0.76
    eele
    -0.75
    EStream
    -0.74
    terday
    -0.74
    ¥µ
    -0.68
    HAEL
    -0.67
    xon
    -0.66
    plane
    -0.65
    Downloadha
    -0.65
    POSITIVE LOGITS
    acent
    1.22
    ainer
    1.01
    icating
    1.01
    antly
    0.94
    icates
    0.93
    iable
    0.85
    iability
    0.83
    ause
    0.83
    icit
    0.82
    isance
    0.82
    Activations Density 0.006%

    No Known Activations