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. 12460
    Prev
    Next
    INDEX
    Explanations

    instances of the word "volume" with various spellings

    oai_token-act-pair · gpt-3.5-turbo

    words related to food, specifically types of cuisine and dishes

    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
    rupted
    -0.66
    fram
    -0.65
    talk
    -0.65
     closing
    -0.62
    ulation
    -0.62
    holm
    -0.60
    bered
    -0.60
    obal
    -0.60
    nell
    -0.58
    apt
    -0.58
    POSITIVE LOGITS
    OPLE
    1.06
    ume
    0.95
    umes
    0.94
    uming
    0.84
    iture
    0.81
    HAHAHAHA
    0.79
    querade
    0.76
    HAHA
    0.75
    UME
    0.74
    urs
    0.74
    Activations Density 0.032%

    No Known Activations