INDEX

Explanations

instances of abstract concepts and theories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

endpush

-0.67

RenderAtEndOf

-0.62

__(/*!

-0.55

UseVisualStyle

-0.53

endregion

-0.53

JsonInclude

-0.51

daß

-0.50

確実に

-0.49

QApplication

-0.49

guchi

-0.48

POSITIVE LOGITS

 abstra

0.98

 abstrak

0.94

 abstraction

0.92

 abstractions

0.89

 abstract

0.87

 Abstra

0.86

 vague

0.84

 abstracta

0.84

 abstracted

0.83

abstra

0.81

Activations Density 0.354%

instances of abstract concepts and theories

No Comments

No Known Activations