INDEX

Explanations

references to specific locations and geographical terms

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Према

-0.68

 kasarigan

-0.63

 getLogin

-0.56

withIdentifier

-0.54

 HttpNotFound

-0.53

ENSIONS

-0.53

DoubleQuotes

-0.53

Décès

-0.52

ONTO

-0.52

útbol

-0.52

POSITIVE LOGITS

 entire

0.71

 hinweg

0.69

 boyunca

0.65

ClientSize

0.64

 verteilt

0.62

 initComponents

0.62

 throughout

0.61

throughout

0.61

 désolés

0.60

 whole

0.57

Activations Density 0.360%

references to specific locations and geographical terms

No Comments

No Known Activations