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. 20855
    Prev
    Next
    INDEX
    Explanations

    phrases related to the name "Osso."

    oai_token-act-pair · gpt-3.5-turbo

    the word "so" and variations of it used in various 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
     tracing
    -0.65
     curves
    -0.64
     deficit
    -0.63
    DERR
    -0.63
     customs
    -0.63
     triangle
    -0.59
     indifference
    -0.59
     homicide
    -0.59
     prose
    -0.59
     appra
    -0.58
    POSITIVE LOGITS
    FTWARE
    1.12
    ppy
    1.06
    bered
    1.04
    oooo
    1.03
    othe
    1.02
    ll
    1.02
    ooo
    1.01
    vere
    1.00
    oner
    0.99
    fter
    0.99
    Activations Density 0.048%

    No Known Activations