INDEX

Explanations

references to individuals or people within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

AndEndTag

-0.56

Diweddarwch

-0.52

Tikang

-0.51

XtraGrid

-0.50

Välislingid

-0.50

 CreateTagHelper

-0.50

 Brew

-0.50

ⓧ

-0.48

 Steep

-0.48

 chivalry

-0.48

POSITIVE LOGITS

 person

1.98

Person

1.92

 Person

1.89

person

1.88

 PERSON

1.66

PERSON

1.58

 persons

1.55

Persons

1.47

 Persons

1.46

persons

1.46

Activations Density 0.133%

references to individuals or people within the text

No Comments

No Known Activations