INDEX

Explanations

specific legal or scientific terminology related to cases and evidence

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 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

WebElementEntity

-0.66

 otomatig

-0.66

 Infórmanos

-0.65

󠁴

-0.61

øya

-0.61

ertor

-0.59

 давайте

-0.59

 maî

-0.57

cuál

-0.56

sidemargin

-0.54

POSITIVE LOGITS

 Buck

0.64

Sprintf

0.63

buck

0.62

BUCK

0.61

Buck

0.60

ENDO

0.58

glBegin

0.56

 buck

0.56

بوابة

0.55

Ren

0.54

Activations Density 2.130%

specific legal or scientific terminology related to cases and evidence

No Comments

No Known Activations