INDEX

Explanations

punctuation marks, specifically apostrophes

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

Apostrophes followed by specific letters

np_acts-logits-general · gemini-2.0-flash

apostrophe followed by s or th

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

 للاسماء

-0.83

 CreateTagHelper

-0.80

Hentet

-0.66

awtextra

-0.66

发表于

-0.65

RegressionTest

-0.65

لينكات

-0.60

 صوتيه

-0.60

 resourceCulture

-0.59

WireFormatLite

-0.57

POSITIVE LOGITS

0.83

 venezolano

0.42

$'

0.42

|'

0.41

#'

0.37

 podamos

0.36

šnje

0.34

Twas

0.33

%'

0.33

 Begleitung

0.33

Activations Density 0.227%

punctuation marks, specifically apostrophes

Apostrophes followed by specific letters

apostrophe followed by s or th

No Comments

No Known Activations