INDEX

Explanations

indicators of personal interest and preference

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 SwitchCompat

-0.99

parsedMessage

-0.94

DockStyle

-0.88

Geplaatst

-0.86

mybatisplus

-0.84

MigrationBuilder

-0.81

 flesta

-0.80

featureID

-0.79

Obrázky

-0.78

 <<<<<<<<<<<<<<

-0.77

POSITIVE LOGITS

 sometimes

0.80

may

0.70

 some

0.67

 Sometimes

0.62

 parfois

0.58

sometimes

0.58

Sometimes

0.57

 maybe

0.52

 even

0.52

ir

0.50

Activations Density 0.336%

indicators of personal interest and preference

No Comments

No Known Activations