© 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. 14073
    Prev
    Next
    INDEX
    Explanations

    instances of the character "Ċ" followed by "10" activation, often occurring at the end of segment boundaries

    oai_token-act-pair · gpt-3.5-turbo

    expressions of evaluation or judgment

    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
     orchestr
    -0.79
     estranged
    -0.77
     elect
    -0.77
     adversaries
    -0.77
     courier
    -0.77
     torpedo
    -0.76
    ¥ŀ
    -0.76
     favoured
    -0.75
     advancing
    -0.74
     decap
    -0.74
    POSITIVE LOGITS
    Anyway
    1.60
    Anonymous
    1.47
    ³³³³³³³³
    1.44
    Posted
    1.40
    ³³³³
    1.33
    Honestly
    1.28
    posted
    1.28
    ³³³
    1.28
    ³³³³³³³³³³³³³³³³
    1.28
    Yeah
    1.26
    Activations Density 0.295%

    No Known Activations