INDEX

Explanations

references to changes in numbers or metrics over time

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

 AssemblyTitle

-0.70

reciate

-0.58

Ecotoxicity

-0.58

 tắc

-0.58

étit

-0.58

utique

-0.57

ôtel

-0.56

ruppen

-0.56

 tremp

-0.54

eclampsia

-0.53

POSITIVE LOGITS

enumii

0.77

 từ

0.75

enumi

0.73

 between

0.66

 FROM

0.63

 From

0.63

 from

0.63

 BETWEEN

0.62

 mellan

0.61

 createState

0.61

Activations Density 0.175%

references to changes in numbers or metrics over time

No Comments

No Known Activations