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. 11744
    Prev
    Next
    INDEX
    Explanations

    word stems or partial words with varying accents or special characters

    oai_token-act-pair · gpt-3.5-turbo

    special characters and non-typical letter combinations, indicating a focus on unique or unusual textual elements

    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
    é»Ĵ
    -0.85
    ongyang
    -0.78
    ccording
    -0.75
    #$#$
    -0.71
     WATCHED
    -0.70
    ecause
    -0.68
    eworthy
    -0.67
    xtap
    -0.66
    é£
    -0.65
     Unloaded
    -0.63
    POSITIVE LOGITS
    enment
    1.01
     coli
    0.71
    enko
    0.67
    hyde
    0.66
     Valencia
    0.65
     Choi
    0.63
    cheon
    0.63
    ciating
    0.63
    oyer
    0.62
     Rangers
    0.61
    Activations Density 0.462%

    No Known Activations