INDEX

Explanations

expressions and sentiments related to emotional responses and social observations

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

followed by punctuation or 'for'/'when'

np_acts-logits-general · gemini-2.0-flash

evaluations of situations

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

 ModelExpression

-0.89

expandindo

-0.81

 Мексичка

-0.80

StoryboardSegue

-0.80

AndEndTag

-0.78

findpost

-0.78

 JpaRepository

-0.76

PMailer

-0.75

DockStyle

-0.73

IUrlHelper

-0.73

POSITIVE LOGITS

 considering

0.72

 sekali

0.61

 tanke

0.59

for

0.58

 given

0.58

 especially

0.54

considering

0.51

 knowing

0.49

if

0.49

Activations Density 0.357%

expressions and sentiments related to emotional responses and social observations

followed by punctuation or 'for'/'when'

evaluations of situations

No Comments

No Known Activations