INDEX

Explanations

instances of the word "suggest" and its variations to identify recommendations or implications in the text

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

preceding "that"

np_acts-logits-general · gemini-2.0-flash

suggests that

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

Wal

-0.68

gdx

-0.66

Biografía

-0.64

wal

-0.61

 immemorial

-0.61

DNI

-0.60

roo

-0.60

WAL

-0.60

DecimalFormat

-0.60

Wal

-0.59

POSITIVE LOGITS

 SUGGEST

1.29

 suggestions

1.27

ugges

1.25

 suggested

1.20

 suggest

1.17

SUGGEST

1.16

 Suggestions

1.16

 Sugges

1.15

 suggestion

1.14

suggestions

1.14

Activations Density 0.116%

instances of the word "suggest" and its variations to identify recommendations or implications in the text

preceding "that"

suggests that

No Comments

No Known Activations