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. 20866
    Prev
    Next
    INDEX
    Explanations

    words related to randomness or random selection

    oai_token-act-pair · gpt-3.5-turbo

    instances of the words "randomly" and "accidentally."

    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
    gers
    -0.78
    antics
    -0.75
    ger
    -0.72
    ador
    -0.70
    rers
    -0.69
     attainment
    -0.68
    soc
    -0.68
    uese
    -0.68
    ryu
    -0.67
    ges
    -0.67
    POSITIVE LOGITS
     detonated
    0.84
     stumbled
    0.80
     worshipped
    0.78
     bumped
    0.76
     located
    0.75
     combust
    0.75
     planted
    0.75
     placed
    0.74
     timed
    0.74
     chose
    0.73
    Activations Density 0.034%

    No Known Activations