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. 10-RES-JB
    6. 6803
    Prev
    Next
    INDEX
    Explanations

    instances of actions or events starting with the phrase "go on"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that begin with "go on" followed by various actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ£
    -0.77
    ollah
    -0.75
    ¯
    -0.73
    iso
    -0.73
    ãĤ§
    -0.66
    OTS
    -0.64
    ãĥķãĤ¡
    -0.62
     Primordial
    -0.61
    redients
    -0.61
    enance
    -0.61
    POSITIVE LOGITS
     hiatus
    1.12
     vacation
    0.95
     strike
    0.86
     pilgrimage
    0.86
     rampage
    0.85
     autop
    0.84
     sale
    0.83
     indefinite
    0.82
     holiday
    0.82
     patrol
    0.81
    Activations Density 0.033%

    No Known Activations