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. 0-RES-JB
    6. 21111
    Prev
    Next
    INDEX
    Explanations

    instances of the word "recruit" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    words related to recruitment and hiring processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Continued
    -0.78
    held
    -0.62
    ylum
    -0.61
    announced
    -0.61
    posted
    -0.60
    Wa
    -0.60
     served
    -0.60
     Ended
    -0.59
    arts
    -0.59
     Continuing
    -0.59
    POSITIVE LOGITS
     recruit
    1.58
     cheat
    1.41
     steal
    1.41
     suppress
    1.41
     acquire
    1.40
     convert
    1.39
     conquer
    1.38
     summon
    1.34
     seize
    1.33
     exploit
    1.33
    Activations Density 0.074%

    No Known Activations