© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 17391
    Prev
    Next
    INDEX
    Explanations

    political and societal commentary related phrases

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character "âĢ" and related symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sled
    -0.72
     Franch
    -0.69
     Manhattan
    -0.63
     Paran
    -0.63
     unmarked
    -0.62
    isode
    -0.61
     velvet
    -0.60
     antip
    -0.60
     Mutual
    -0.59
     Cookie
    -0.59
    POSITIVE LOGITS
    ¬
    1.39
    Ļ
    1.37
    ¡
    1.25
    ľ
    1.21
    Ĵ
    1.19
    ĸ
    1.15
    ı
    1.15
    µ
    1.14
    ¤
    1.11
    Ĺ
    1.11
    Activations Density 0.336%

    No Known Activations