INDEX

Explanations

phrases associated with significant impact or influence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

もはや

-0.61

 Bellini

-0.59

CppCodeGen

-0.57

 deadliest

-0.57

GEBURTSDATUM

-0.57

 eterna

-0.54

 fallait

-0.54

 eterno

-0.54

┻

-0.54

 poveznice

-0.53

POSITIVE LOGITS

 sekali

0.87

 alot

0.80

 מאוד

0.77

sehr

0.73

BibitemShut

0.73

 heavily

0.71

 ExecuteAsync

0.71

alot

0.71

Lots

0.70

 itſelf

0.69

Activations Density 0.332%

phrases associated with significant impact or influence

No Comments

No Known Activations