INDEX

Explanations

interrogative phrases that seek clarification or information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

PreInfinity

-0.71

ؤلاء

-0.71

니다

-0.67

 صوتيه

-0.67

äten

-0.63

 הזה

-0.63

 समीक्षक

-0.63

iestety

-0.61

енча

-0.61

expandindo

-0.60

POSITIVE LOGITS

 What

1.04

What

1.04

How

0.98

How

0.98

what

0.88

 WHAT

0.84

WHAT

0.82

how

0.81

Why

0.81

Why

0.80

Activations Density 0.185%

interrogative phrases that seek clarification or information

No Comments

No Known Activations