INDEX

Explanations

positive actions or descriptors related to audience engagement and recognition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.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

#+#

-0.78

PreferredItem

-0.67

BufferException

-0.65

BeginContext

-0.61

ⓧ

-0.61

rungsseite

-0.59

itename

-0.58

ponses

-0.58

ciclopedia

-0.57

ніципа

-0.56

POSITIVE LOGITS

 audiences

1.34

 audience

1.19

audience

0.91

Audience

0.85

Audiences

0.84

audi

0.83

 Audience

0.83

 viewers

0.81

 crowds

0.80

 ауди

0.78

Activations Density 0.310%

positive actions or descriptors related to audience engagement and recognition

No Comments

No Known Activations