INDEX

Explanations

lines or segments containing references to data structure or formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

ceğine

-0.58

IsMutable

-0.54

 Lightboxes

-0.53

Chham

-0.51

foss

-0.49

objectId

-0.49

پیوند

-0.48

olate

-0.47

#+#

-0.45

 criança

-0.45

POSITIVE LOGITS

 name

0.68

 getName

0.63

 title

0.61

 Name

0.61

name

0.61

setTitle

0.60

Name

0.60

 setTitle

0.59

 NAME

0.59

entitled

0.58

Activations Density 0.165%

lines or segments containing references to data structure or formatting

No Comments

No Known Activations