INDEX

Explanations

references to experimental data and methodologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 للاسماء

-0.87

 createState

-0.72

Viited

-0.60

Hentet

-0.57

sizeCache

-0.55

HasForeignKey

-0.54

يكب

-0.52

UnknownFields

-0.51

ViewImports

-0.50

UnifiedTopology

-0.50

POSITIVE LOGITS

httphttps

0.62

ַל

0.61

 esimer

0.60

NewUrlParser

0.60

δες

0.60

󠁢

0.57

 Vikipedi

0.57

xins

0.56

 xlink

0.55

vation

0.55

Activations Density 0.505%

references to experimental data and methodologies

No Comments

No Known Activations