INDEX

Explanations

numbers or values presented in a structured format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tė

-0.59

 bocca

-0.58

 femmin

-0.56

 tarko

-0.56

 efectivamente

-0.53

 réguli

-0.53

 religieuses

-0.53

Efq

-0.53

unnitel

-0.53

 võimal

-0.52

POSITIVE LOGITS

tagHelperRunner

1.09

ViewFeatures

0.75

/**

0.69

تقاوى

0.67

enumi

0.64

<bos>

0.63

 liga

0.61

WebVitals

0.61

 eventdata

0.60

Activations Density 0.537%

numbers or values presented in a structured format

No Comments

No Known Activations