INDEX

Explanations

instances of the word "does"

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

 Leal

-0.69

ing

-0.67

tmpl

-0.63

artement

-0.62

 Gull

-0.62

 <<<<<<<<<<<<<<

-0.60

 McCartney

-0.60

 merid

-0.59

▾

-0.59

اعدة

-0.59

POSITIVE LOGITS

 Does

1.91

 does

1.86

Does

1.85

does

1.78

 DOES

1.72

DOES

1.61

DID

1.19

do

1.15

doe

1.13

Did

1.12

Activations Density 0.127%

instances of the word "does"

No Comments

No Known Activations