INDEX

Explanations

phrases related to duration and experience

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

ConstraintMaker

-0.87

ędziesz

-0.84

\{\\

-0.84

signable

-0.77

("]");

-0.76

 purpoſe

-0.75

 himſelf

-0.75

mejores

-0.75

ądź

-0.75

 Monfieur

-0.74

POSITIVE LOGITS

 years

1.61

 Years

1.35

 YEARS

1.26

years

1.26

 Jahre

1.24

Years

1.22

yrs

1.06

 Jahren

1.05

 años

1.04

YEARS

1.03

Activations Density 0.070%

phrases related to duration and experience

No Comments

No Known Activations