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. 8-RES-JB
    6. 14612
    Prev
    Next
    INDEX
    Explanations

    phrases containing foreign characters or symbols

    oai_token-act-pair · gpt-3.5-turbo

    the character 'ĥ' repeated in various contexts

    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
     relevance
    -0.70
     Sparkle
    -0.66
     closest
    -0.66
     override
    -0.66
     exactly
    -0.64
     mathemat
    -0.61
     charism
    -0.61
     Wally
    -0.59
    baugh
    -0.58
     approximate
    -0.58
    POSITIVE LOGITS
    ÏĦ
    1.17
    ña
    0.96
    Ct
    0.95
    é¾įåĸļ士
    0.94
    ontent
    0.92
    ime
    0.89
    ¸
    0.88
    ¤
    0.85
    ı
    0.83
    ο
    0.83
    Activations Density 0.014%

    No Known Activations