INDEX

Explanations

references to programming concepts and terminology

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

utenants

-0.72

ه

-0.69

letoe

-0.67

-0.65

phrag

-0.62

Slf

-0.60

dew

-0.59

-0.58

-0.56

POSITIVE LOGITS

 myſelf

1.04

 himſelf

1.03

ſelf

1.02

 itſelf

1.01

 themſelves

0.99

ſelves

0.94

 paſſ

0.94

 enfans

0.88

 ſmall

0.86

;">

0.86

Activations Density 1.782%

references to programming concepts and terminology

No Comments

No Known Activations