INDEX

Explanations

references to locations or states of being, particularly "inside" and "outside."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cillor

-0.78

formin

-0.72

}`

-0.70

archical

-0.70

REEK

-0.69

ambung

-0.69

esgue

-0.69

CHELL

-0.68

apunov

-0.66

ntlet

-0.66

POSITIVE LOGITS

 Inside

1.27

Inside

1.23

 INSIDE

1.23

 inside

1.21

inside

1.20

 InputDecoration

1.16

INSIDE

1.12

 Outside

1.10

OUTSIDE

1.06

Outside

1.03

Activations Density 0.058%

references to locations or states of being, particularly "inside" and "outside."

No Comments

No Known Activations