INDEX

Explanations

words related to specific properties or characteristics

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

 فريبيس

-0.75

 Torna

-0.60

 مرئيه

-0.59

########.

-0.58

 Normdatei

-0.56

CDCl

-0.56

 Italijani

-0.54

Välislingid

-0.53

 мәкал

-0.53

خصة

-0.52

POSITIVE LOGITS

tic

3.15

TIC

1.25

Tic

1.24

ticum

1.09

ticity

1.02

tics

0.99

ETIC

0.94

tic

0.91

Tic

0.89

tică

0.87

Activations Density 0.062%

words related to specific properties or characteristics

No Comments

No Known Activations