INDEX

Explanations

markup and formatting tags in a structured data context

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 оригіналу

-0.89

Rhestr

-0.86

 kasarigan

-0.86

 doubtnut

-0.85

httphttps

-0.80

mybatisplus

-0.79

 Италијани

-0.78

 myſelf

-0.77

 himſelf

-0.75

 AttributeSet

-0.75

POSITIVE LOGITS

0.58

<eos>

0.50

↵↵

0.49

0.47

0.46

 main

0.46

For

0.45

Activations Density 0.257%

markup and formatting tags in a structured data context

No Comments

No Known Activations