INDEX

Explanations

references to significant organizations and entities in various sectors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

__).

-0.63

teness

-0.60

xase

-0.57

Géographie

-0.56

Progress

-0.54

 Progress

-0.53

وث

-0.52

verläs

-0.52

 tả

-0.51

ardin

-0.51

POSITIVE LOGITS

 renom

0.67

 prestigious

0.61

 giants

0.60

 prestig

0.60

 GoogleFonts

0.57

 renowned

0.57

renowned

0.56

famous

0.56

 famous

0.55

BeginContext

0.55

Activations Density 0.254%

references to significant organizations and entities in various sectors

No Comments

No Known Activations