INDEX

Explanations

connections and associations in text regarding media influence or misinformation

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

 visuals

-0.79

 visually

-0.76

 visualize

-0.76

Visual

-0.75

 visual

-0.75

 Visual

-0.75

 visualization

-0.74

 visualized

-0.74

 Visualization

-0.73

visual

-0.71

POSITIVE LOGITS

 sound

0.77

 SOUND

0.74

 caption

0.72

 audio

0.72

sound

0.70

SOUND

0.68

 smell

0.68

 sounds

0.67

 Sound

0.66

Sound

0.66

Activations Density 0.277%

connections and associations in text regarding media influence or misinformation

No Comments

No Known Activations