INDEX

Explanations

references to profiles, particularly in the context of social media or personal identification

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

"profile" and "profiles"

np_acts-logits-general · gemini-2.0-flash

profile details

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 елның

-0.64

Bolt

-0.63

 EdgeInsets

-0.60

 domestique

-0.60

İstinadlar

-0.58

$"

-0.58

MockMvc

-0.58

NESS

-0.58

tst

-0.58

程度上

-0.58

POSITIVE LOGITS

 profiles

1.20

 Profiles

1.05

Profiles

1.01

profiles

1.00

 profile

0.95

 Profile

0.87

 perfiles

0.86

 PROFILE

0.84

PROFILE

0.78

 profil

0.76

Activations Density 0.084%

references to profiles, particularly in the context of social media or personal identification

"profile" and "profiles"

profile details

No Comments

No Known Activations