INDEX

Explanations

punctuation and formatting markers in the text

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 espirituales

-0.67

 chré

-0.60

 vectorielles

-0.59

 religieuses

-0.58

 nicio

-0.56

mặt

-0.55

hasOwnProperty

-0.54

 ácido

-0.53

 enfans

-0.53

 vertes

-0.53

POSITIVE LOGITS

Lon

0.63

+#+#

0.61

 Tham

0.59

 lenker

0.58

nemia

0.57

aarrggbb

0.57

expandindo

0.57

featureID

0.57

 Asta

0.55

escence

0.55

Activations Density 0.092%

punctuation and formatting markers in the text

No Comments

No Known Activations