INDEX

Explanations

code elements indicating programming functionality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 newBuilder

-0.61

حياته

-0.56

inição

-0.54

 Havel

-0.53

Према

-0.52

 except

-0.50

 createState

-0.50

proper

-0.50

ьаж

-0.49

 dAtA

-0.47

POSITIVE LOGITS

expandindo

0.67

<eos>

0.63

تقاوى

0.63

↵↵

0.62

Hochspringen

0.61

 telescopic

0.60

 adjourned

0.57

 terus

0.56

határoz

0.56

Personensuche

0.55

Activations Density 0.067%

code elements indicating programming functionality

No Comments

No Known Activations