Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 7138
    Prev
    Next
    INDEX
    Explanations

    words containing the sequence "rom" preceded by a digit

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "rom" in different contexts, likely indicating a focus on romance or romantic themes

    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
     Rapids
    -0.69
     threshold
    -0.66
     Jackets
    -0.65
     reminders
    -0.64
     fide
    -0.63
     Padres
    -0.61
     Reserve
    -0.61
    Notes
    -0.60
     haste
    -0.60
     caveat
    -0.59
    POSITIVE LOGITS
    antic
    1.26
    ecast
    1.21
    ancers
    1.16
    agnetic
    1.11
    astery
    1.10
    antically
    1.05
    antics
    1.04
    ancer
    1.00
    atic
    0.98
    edy
    0.96
    Activations Density 0.019%

    No Known Activations