INDEX

Explanations

mentions of "character" and related 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

AddTagHelper

-1.06

Tipp

-0.81

 faſt

-0.80

 myſelf

-0.79

SPS

-0.76

 تضيفلها

-0.75

 impunity

-0.74

 Thine

-0.73

 morrow

-0.72

 againſt

-0.71

POSITIVE LOGITS

 character

2.41

 characters

2.29

character

2.10

 Character

2.09

 CHARACTER

2.03

characters

2.00

 Characters

1.92

Character

1.92

Characters

1.73

 karakter

1.67

Activations Density 0.047%

mentions of "character" and related terms

No Comments

No Known Activations