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. 2557
    Prev
    Next
    INDEX
    Explanations

    words containing the substring "app" with varying intensities

    oai_token-act-pair · gpt-3.5-turbo

    the word "app" in various forms or contexts

    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
    EStreamFrame
    -0.77
    κ
    -0.67
     caution
    -0.67
     guiActiveUn
    -0.66
     sidx
    -0.65
     formal
    -0.63
    trl
    -0.63
     maj
    -0.62
     knot
    -0.61
     sqor
    -0.61
    POSITIVE LOGITS
    earance
    1.56
    ears
    1.35
    ointment
    1.33
    alach
    1.27
    earances
    1.27
    lied
    1.25
    eared
    1.24
    arently
    1.22
    arent
    1.12
    earing
    1.07
    Activations Density 0.011%

    No Known Activations