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. 8-RES-JB
    6. 23105
    Prev
    Next
    INDEX
    Explanations

    words related to hostage situations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of hostage situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atism
    -0.71
    ector
    -0.68
    iegel
    -0.67
    Spread
    -0.67
    hem
    -0.66
    hemy
    -0.65
    MJ
    -0.65
    aturdays
    -0.63
    sburgh
    -0.63
     Bore
    -0.63
    POSITIVE LOGITS
    ele
    0.91
    serv
    0.86
     negotiator
    0.84
     maid
    0.78
    Bey
    0.78
     negotiators
    0.76
     pets
    0.74
     pige
    0.73
     bargaining
    0.70
     servant
    0.70
    Activations Density 0.078%

    No Known Activations