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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 16814
    Prev
    Next
    INDEX
    Explanations

    terms related to institutions, financial entities, and governmental bodies

    oai_token-act-pair · gpt-3.5-turbo

    references to "hem" or related word forms, indicating a focus on specific terminology or names associated with it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Peaks
    -0.77
    âķIJ
    -0.69
    emonium
    -0.67
     AVG
    -0.66
    çĶŁ
    -0.65
     Oro
    -0.63
    ULTS
    -0.61
     senses
    -0.61
    xtap
    -0.59
    ÄŁ
    -0.59
    POSITIVE LOGITS
    oglobin
    1.18
    isphere
    0.98
    icals
    0.97
    oths
    0.97
    ilk
    0.92
    med
    0.90
    ovie
    0.87
    icol
    0.87
    ming
    0.84
    useum
    0.83
    Activations Density 0.023%

    No Known Activations