INDEX

Explanations

references to specific nouns and pronouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 CreateTagHelper

-0.79

]")]

-0.73

 autorytatywna

-0.72

 isNameExpr

-0.71

%");

-0.70

verifyException

-0.70

NameInMap

-0.69

?>">

-0.69

 kasarigan

-0.69

 שוליים

-0.67

POSITIVE LOGITS

 went

0.71

 flew

0.70

 came

0.65

 didn

0.62

did

0.60

 laughed

0.60

 responded

0.59

 toured

0.59

 looked

0.59

 threw

0.58

Activations Density 0.460%

references to specific nouns and pronouns

No Comments

No Known Activations