INDEX

Explanations

references to people or persons in various contexts

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

TagHelpers

-0.79

>\<^

-0.79

gemar

-0.76

ReadAll

-0.75

hysema

-0.75

warded

-0.74

NewLabel

-0.73

Rie

-0.72

immobili

-0.72

 Aeronau

-0.72

POSITIVE LOGITS

 Person

2.21

 person

2.19

person

2.06

 Persons

2.03

Person

2.03

 PERSON

2.02

PERSON

1.89

Persons

1.87

 persons

1.86

persons

1.82

Activations Density 0.047%

references to people or persons in various contexts

No Comments

No Known Activations