INDEX

Explanations

references to historical landmarks and ruins

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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



-0.76

AddTagHelper

-0.61

astify

-0.59

onomian

-0.54

WriteTagHelper

-0.53

abestanden

-0.53

achal

-0.52

providedIn

-0.50

lemény

-0.48

 Scranton

-0.48

POSITIVE LOGITS

 Picchu

0.76

Archae

0.64

 archaeological

0.64

 structures

0.63

yntaxException

0.63

 ruins

0.62

 Archae

0.60

 excavated

0.60

IBOutlet

0.60

setVerticalGroup

0.59

Activations Density 0.161%

references to historical landmarks and ruins

No Comments

No Known Activations