INDEX

Explanations

contexts involving controversy or conflict

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 المعيارى

-0.75

Попис

-0.72

 tartalomajánló

-0.69

 Roskov

-0.66

 للاسماء

-0.63

tagHelperRunner

-0.62

SerializedSize

-0.62

ynchrotron

-0.61

'}),

-0.60

umab

-0.59

POSITIVE LOGITS

 receive

0.65

Personendaten

0.59

 earn

0.57

会被

0.55

 qualify

0.53

 receives

0.52

 mendapat

0.52

 attracting

0.52

glPopMatrix

0.52

 attract

0.51

Activations Density 0.528%

contexts involving controversy or conflict

No Comments

No Known Activations