INDEX

Explanations

references to geographical or historical entities with political significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

tagHelperRunner

-0.60

requireNonNull

-0.60

anyahu

-0.56

脚注の使い方

-0.56

 Widodo

-0.53

قایناق‌لار

-0.51

__(/*!

-0.49

individual

-0.49

 individual

-0.49

 beginnetje

-0.49

POSITIVE LOGITS

 témoin

0.61

ịch

0.59

 testigo

0.58

untos

0.58

SBATCH

0.57

 vidare

0.57

enschappelijke

0.57

 reins

0.54

 steered

0.53

edan

0.53

Activations Density 0.492%

references to geographical or historical entities with political significance

No Comments

No Known Activations