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. 10330
    Prev
    Next
    INDEX
    Explanations

    words formed by the capital letters in a specific pattern

    oai_token-act-pair · gpt-3.5-turbo

    the presence of promotional language and advertisement terminology

    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
    Gene
    -0.72
    Bug
    -0.71
    acus
    -0.71
    pmwiki
    -0.69
    itsch
    -0.66
     Cut
    -0.65
    Spring
    -0.63
     Guilty
    -0.63
    Cent
    -0.63
    sbm
    -0.63
    POSITIVE LOGITS
    xon
    0.68
    stood
    0.64
     Âł Âł
    0.63
     converter
    0.62
    ordinary
    0.62
     stride
    0.62
    ŃĶ
    0.62
    FACE
    0.62
    illion
    0.60
    apeshifter
    0.60
    Activations Density 0.182%

    No Known Activations