INDEX

Explanations

phrases or statements related to opinions and comments about evidence or events in political or social contexts

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

Names followed by "said"

np_acts-logits-general · gemini-2.0-flash

names followed by said

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 виправивши

-0.65

WriteTagHelper

-0.64

 تضيفلها

-0.63

 censiti

-0.63

interopRequire

-0.60

AndEndTag

-0.57

 يتيمه

-0.57

存于互联网档案馆

-0.55

tvguidetime

-0.55

dafx

-0.52

POSITIVE LOGITS

 said

3.49

said

2.21

 SAID

1.97

Said

1.92

 Said

1.85

 faid

1.66

 dijo

1.54

 gezegd

1.47

 detto

1.36

 sagte

1.29

Activations Density 0.354%

phrases or statements related to opinions and comments about evidence or events in political or social contexts

Names followed by "said"

names followed by said

No Comments

No Known Activations