INDEX

Explanations

references to specific cases and models in a theoretical or scientific context

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

AndEndTag

-0.75

__':

-0.72

 jadx

-0.71

TestTools

-0.71

 itſelf

-0.70

__":

-0.70

GIVEREF

-0.70

ulement

-0.66

tonsoft

-0.66

bibfield

-0.66

POSITIVE LOGITS

 case

1.18

 cases

1.14

 casos

1.10

 caso

1.05

 cazul

0.98

case

0.98

 kasus

0.92

 scenarios

0.91

 scenario

0.89

 situations

0.89

Activations Density 1.137%

references to specific cases and models in a theoretical or scientific context

No Comments

No Known Activations