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. 2568
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to hotels or locations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Ritz" associated with various contexts or mentions

    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
     livest
    -0.76
     Pradesh
    -0.68
     unden
    -0.67
    Interstitial
    -0.65
     arming
    -0.65
    ACTED
    -0.65
     notor
    -0.65
    auga
    -0.64
    cknow
    -0.63
     occas
    -0.63
    POSITIVE LOGITS
    gerald
    1.64
    patrick
    1.21
    sch
    1.15
    itz
    1.08
    heimer
    1.05
    enger
    1.00
    aic
    0.94
    enegger
    0.93
    roth
    0.93
    geist
    0.89
    Activations Density 0.016%

    No Known Activations