INDEX

Explanations

expressions of uncertainty or opinions regarding clarity and quality

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

"Not" followed by an adjective or adverb

np_acts-logits-general · gemini-2.0-flash

not much

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

 صوتيه

-0.52

 متحده

-0.48

HasAnnotation

-0.47

 vVar

-0.47

 jopa

-0.42

 kuitenkin

-0.42

iyle

-0.41

 IFTT

-0.40

 piatta

-0.40

 persino

-0.40

POSITIVE LOGITS

 anymore

0.97

nor

0.91

tagHelperRunner

0.80

 transfieras

0.63

而是

0.61

IsContent

0.61

 necessarily

0.59

nor

0.58

 Tampoco

0.56

 ब्रेकडाउन

0.56

Activations Density 0.719%

expressions of uncertainty or opinions regarding clarity and quality

"Not" followed by an adjective or adverb

not much

No Comments

No Known Activations