INDEX

Explanations

phrases related to evaluating performance or quality of work

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

Positive feedback on performance

np_acts-logits-general · gemini-2.0-flash

positive job assessment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

esModule

-0.82

Tikang

-0.73

TagMode

-0.72

afficheront

-0.71

出版年

-0.70

-0.66

COUVER

-0.65

isContained

-0.65

aarrggbb

-0.64

ngdoc

-0.63

POSITIVE LOGITS

job

2.62

job

2.20

Job

2.04

Job

2.01

JOB

1.94

 jobs

1.74

JOB

1.69

jobs

1.55

 jobb

1.50

 Jobs

1.46

Activations Density 0.095%

phrases related to evaluating performance or quality of work

Positive feedback on performance

positive job assessment

No Comments

No Known Activations