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. 9-RES-JB
    6. 911
    Prev
    Next
    INDEX
    Explanations

    names, likely celebrity names, and possibly professional titles

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific character or entity, denoted by the symbol "âĢ"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     interf
    -0.76
     comprom
    -0.68
    market
    -0.67
    theless
    -0.67
     traffic
    -0.66
     photoc
    -0.66
     STATS
    -0.65
     MET
    -0.64
     decomp
    -0.64
     extrap
    -0.62
    POSITIVE LOGITS
    Ļ
    1.52
    ¬
    1.40
    ¡
    1.32
    ´
    1.26
    £
    1.25
    ĺ
    1.24
    ¤
    1.24
    ¥
    1.22
    §
    1.22
    ¶
    1.21
    Activations Density 0.225%

    No Known Activations