INDEX

Explanations

instances of variable names in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ing

-0.68

on

-0.63

zea

-0.62

 rive

-0.61

ation

-0.60

bour

-0.58

↵↵

-0.58

<strong>

-0.58

met

-0.56

伽

-0.56

POSITIVE LOGITS

obj

1.66

obj

1.59

Obj

1.28

OBJ

1.22

Obj

1.21

 виправивши

1.14

 objs

1.11

objs

1.05

 OBJECTIVE

1.04

 betweenstory

1.03

Activations Density 0.026%

instances of variable names in code

No Comments

No Known Activations