INDEX

Explanations

terms related to agents, agency, and salt

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

Autoritní

-0.43

sizeCache

-0.39

ंदीखरीदारी

-0.38

 ComVisible

-0.36

 Lokales

-0.35

StoreMessageInfo

-0.35

よいよ

-0.34

">//

-0.34

 заявил

-0.34

lze

-0.34

POSITIVE LOGITS

 experiment

0.83

 agent

0.68

 agencies

0.65

 agents

0.65

Tikang

0.64

experiment

0.63

 EXPERIMENT

0.63

 Agents

0.62

 agente

0.61

 ſei

0.61

Activations Density 0.172%

terms related to agents, agency, and salt

No Comments

No Known Activations