INDEX

Explanations

instances of the word "used" and its variants in various contexts

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

ConstraintMaker

-0.99

 BorderRadius

-0.98

 MessageBoxIcon

-0.94

ValueStyle

-0.94

:✨

-0.93

SuppressLint

-0.88

 chakras

-0.86

 categoryId

-0.85

 bezeichneter

-0.83

PSM

-0.83

POSITIVE LOGITS

use

1.04

 used

0.98

USE

0.95

setUse

0.94

USE

0.92

Use

0.92

 uses

0.89

ToUse

0.87

 USED

0.86

Use

0.85

Activations Density 0.213%

instances of the word "used" and its variants in various contexts

No Comments

No Known Activations