INDEX

Explanations

words or short phrases that indicate helpfulness or are part of a directive

oai_token-act-pair · gemini-2.0-flash

including/incorporating

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

findpost

-0.77

RectangleBorder

-0.76

 مشين

-0.68

Sucesor

-0.65

ViewImports

-0.62

 unknownFields

-0.59



-0.56

brainly

-0.54

 nawr

-0.54

hoea

-0.54

POSITIVE LOGITS

 inclusion

1.93

 included

1.88

 Included

1.75

 incorporate

1.71

included

1.70

 Inclusion

1.67

Included

1.67

Include

1.66

 Include

1.65

 include

1.64

Activations Density 2.666%

words or short phrases that indicate helpfulness or are part of a directive

including/incorporating

No Comments

No Known Activations