INDEX

Explanations

references to mathematical operations and logical expressions

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

in

-0.41

occhio

-0.41

-0.40

éndolo

-0.38

éhez

-0.38

-0.37

 đối

-0.37

 Skar

-0.37

POSITIVE LOGITS

 betweenstory

0.96

 للمعارف

0.82

 Jefus

0.79

 Majefty

0.79

 myſelf

0.79

出版年

0.79

 bezeichneter

0.77

ſelves

0.75

 виправивши

0.74

 doubtnut

0.73

Activations Density 0.435%

references to mathematical operations and logical expressions

No Comments

No Known Activations