INDEX

Explanations

conjunctions, particularly the word "and."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

stdc

-0.70

RTSC

-0.64

ſelf

-0.61

 gynhyrchwyd

-0.60

RetentionPolicy

-0.59

Cordialement

-0.57

 OnInit

-0.57

RegressionTest

-0.56

 NgModule

-0.56

xffffff

-0.55

POSITIVE LOGITS

 שוליים

0.81

fortawesome

0.75

 kasarigan

0.74

たまた

0.69

Hozzáférés

0.63

GraphicsUnit

0.60

>−</

0.59

 zwar

0.58

يميديا

0.57

awtextra

0.57

Activations Density 0.321%

conjunctions, particularly the word "and."

No Comments

No Known Activations