INDEX

Explanations

expressions of personal assessment or discovery

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

Chham

-0.76

 '\\;'

-0.75

yntaxException

-0.73

msgTypes

-0.68

httphttps

-0.68

DockStyle

-0.67

 виправивши

-0.66

OGND

-0.65

InputBorder

-0.65

IntoConstraints

-0.64

POSITIVE LOGITS

 finds

0.71

覺得

0.65

 synes

0.65

觉得

0.63

 jugé

0.62

finds

0.62

 feels

0.61

 Finds

0.61

find

0.60

我觉得

0.60

Activations Density 0.260%

expressions of personal assessment or discovery

No Comments

No Known Activations