INDEX

Explanations

words and phrases indicating a sense of familiarity

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

PRNewswire

-0.72

 mourut

-0.71

bigoplus

-0.69

GenerationType

-0.68

 kasarigan

-0.68

iettivo

-0.68

RunAsync

-0.66

ArrowToggle

-0.65

 springfox

-0.63

 Yash

-0.62

POSITIVE LOGITS

 familiar

3.74

familiar

3.35

 Familiar

3.12

Familiar

3.01

 familiarity

2.63

 famili

2.26

famili

2.11

 unfamiliar

2.05

 familiarize

2.01

 acquainted

1.93

Activations Density 0.047%

words and phrases indicating a sense of familiarity

No Comments

No Known Activations