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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 15860
    Prev
    Next
    INDEX
    Explanations

    special characters which likely indicate the end of text segments

    oai_token-act-pair · gpt-3.5-turbo

    expressions of frustration or strong negative sentiment

    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
     disse
    -0.81
     snail
    -0.77
     mesmer
    -0.70
     continental
    -0.68
     antip
    -0.68
     hemor
    -0.67
     seiz
    -0.67
     mimic
    -0.66
     mainland
    -0.66
     Franch
    -0.65
    POSITIVE LOGITS
    Ŀ
    1.90
    ¡
    1.57
    Ĵ
    1.31
    ª
    1.28
    Ķ
    1.28
    ¦
    1.26
    ¤
    1.24
    ľ
    1.23
    ©
    1.23
    ī
    1.23
    Activations Density 0.222%

    No Known Activations