INDEX

Explanations

references to various aspects and elements within a larger context or system

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

"of the"

np_acts-logits-general · gemini-2.0-flash

some of the most

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

weeney

-0.54

two

-0.51

enda

-0.49

MigrationBuilder

-0.49

Portály

-0.48

Hauptartikel

-0.47

am

-0.47

prava

-0.47

الدراسه

-0.46

POSITIVE LOGITS

 poorest

0.77

 brightest

0.74

 hottest

0.73

 freshest

0.72

 richest

0.71

 purest

0.69

 happiest

0.68

 estimés

0.67

 smartest

0.67

 wealthiest

0.67

Activations Density 0.073%

references to various aspects and elements within a larger context or system

"of the"

some of the most

No Comments

No Known Activations