INDEX

Explanations

negative sentiments and expressions of disillusionment

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

Questions, qualifiers, and subsequent words expressing doubt or insignificance

np_acts-logits-general · gemini-2.0-flash

not important

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

енча

-0.61

SPATH

-0.56

المناصب

-0.56

rrggbb

-0.52

 mixt

-0.52

 Paglinawan

-0.48

 Möglich

-0.48

estors

-0.48

 BoxFit

-0.47

 complémentaires

-0.47

POSITIVE LOGITS

 meaningless

1.16

 insignificant

1.13

 unimportant

1.11

 irrelevant

1.05

 hardly

1.01

 pointless

0.96

 useless

0.96

 negligible

0.95

 Hardly

0.93

 worthless

0.91

Activations Density 0.575%

negative sentiments and expressions of disillusionment

Questions, qualifiers, and subsequent words expressing doubt or insignificance

not important

No Comments

No Known Activations