INDEX

Explanations

occurrences of listing phrases or commands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

ists

-0.58

hoots

-0.53

ist

-0.51

hdashline

-0.50

List

-0.49

batore

-0.49

istanbul

-0.48

️

-0.48

liquid

-0.48

bleau

-0.48

POSITIVE LOGITS

PreferredItem

0.87

enable

0.70

 comprehension

0.68

owel

0.67

expandindo

0.67

ENER

0.66

agem

0.66

ened

0.65

serv

0.65

setVerticalGroup

0.63

Activations Density 0.108%

occurrences of listing phrases or commands

No Comments

No Known Activations