INDEX

Explanations

references to agents and character roles in contexts relating to authority or enforcement

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

 تضيفلها

-0.77

chability

-0.76

__*/

-0.67

__(/*!

-0.66

 BeautifulSoup

-0.65

TagMode

-0.64

 Semantics

-0.63

StoryboardSegue

-0.63

Lähteet

-0.62

 nahilalakip

-0.62

POSITIVE LOGITS

 agents

1.12

Agents

1.05

 Agents

1.00

 agencies

0.98

agents

0.97

 AGENTS

0.92

 Agencies

0.91

 agent

0.90

 AGENT

0.89

 AGENCY

0.88

Activations Density 0.147%

references to agents and character roles in contexts relating to authority or enforcement

No Comments

No Known Activations