INDEX

Explanations

descriptions of qualities or attributes, particularly focusing on compliance, efficiency, and effectiveness

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

ending in "-able," "-ive," "-al," or "-ic"

np_acts-logits-general · gemini-2.0-flash

state or manner

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 referenties

-0.70

]<<"

-0.66

]<=

-0.66

writerow

-0.66

SPATH

-0.65

اریخ

-0.64

 насељу

-0.64

--)

-0.64

 Normdatei

-0.64

ագրություններ

-0.64

POSITIVE LOGITS

 fashion

0.71

 format

0.60

 manner

0.59

fashion

0.59

 biçim

0.57

 alimentaires

0.56

Fashion

0.56

 måte

0.55

way

0.54

FunctionFlags

0.53

Activations Density 0.225%

descriptions of qualities or attributes, particularly focusing on compliance, efficiency, and effectiveness

ending in "-able," "-ive," "-al," or "-ic"

state or manner

No Comments

No Known Activations