INDEX

Explanations

positive adjectives and phrases that describe enjoyable experiences or recommendations

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

describing use or quality

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

ocz

-0.31

észetes

-0.31

 joined

-0.29

 najczęściej

-0.29

lamino

-0.28

import

-0.28

 manio

-0.27

 breathed

-0.27

nyataan

-0.26

 entram

-0.26

POSITIVE LOGITS

évaluateur

0.90

tagHelperRunner

0.78

RenderAtEndOf

0.75

+#+#

0.69

 InputDecoration

0.69

msgTypes

0.66

Efq

0.66

 beſch

0.66

HasAnnotation

0.65

 Majefty

0.64

Activations Density 0.014%

positive adjectives and phrases that describe enjoyable experiences or recommendations

describing use or quality

No Comments

No Known Activations