INDEX

Explanations

references to entities or actions associated with user interactions and decisions in a system

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

aarrggbb

-1.23

Билгалдахарш

-1.20

+#+#

-1.16

StoryboardSegue

-1.10

 '\\;'

-1.10

extAlignment

-1.08

 Theſe

-1.05

 مشين

-1.05

featureID

-1.05

 pleaſure

-1.01

POSITIVE LOGITS

0.57

↵↵

0.56

↵

0.55

0.54

↵↵↵

0.54

0.52

0.50

...

0.46

0.45

Activations Density 2.575%

references to entities or actions associated with user interactions and decisions in a system

No Comments

No Known Activations