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. 2569
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of people

    oai_token-act-pair · gpt-3.5-turbo

    references to notable individuals, specifically filmmakers and politicians

    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
     Tune
    -0.74
     antioxid
    -0.68
    yang
    -0.62
     Duck
    -0.61
     XD
    -0.61
     Tayyip
    -0.61
     Erdogan
    -0.60
     Pok
    -0.60
    eering
    -0.60
     Takeru
    -0.59
    POSITIVE LOGITS
    owship
    1.29
    ritch
    0.92
    ats
    0.83
    ows
    0.83
    nuts
    0.80
    Winged
    0.77
    atan
    0.77
    ecided
    0.76
    umbs
    0.76
    angel
    0.74
    Activations Density 0.032%

    No Known Activations