INDEX

Explanations

references to the number three or associated terms

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

../../../

-0.79

 Johnston

-0.78

frow

-0.74

 González

-0.72

wwwwwwww

-0.71

UnknownFields

-0.69

Johnston

-0.68

 Juana

-0.68

spesies

-0.67

 manqué

-0.67

POSITIVE LOGITS

1.82

 Three

1.29

rd

1.28

THREE

1.25

 THREE

1.23

Three

1.19

iii

1.19

three

1.16

三

1.16

 three

1.13

Activations Density 0.196%

references to the number three or associated terms

No Comments

No Known Activations