INDEX

Explanations

expressions focusing on personal experiences and narratives

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

lective

-0.53

urable

-0.52

ebi

-0.51

 Maury

-0.50

 dié

-0.50

("")]

-0.48

 pelican

-0.48

 noma

-0.48

 approximate

-0.47

 wearer

-0.47

POSITIVE LOGITS

+#+

0.77

MockBean

0.73

 weird

0.70

Enllaces

0.69

Anyways

0.67

 disant

0.66

guys

0.65

weird

0.64

 Biôgrafia

0.64

guy

0.64

Activations Density 0.091%

expressions focusing on personal experiences and narratives

No Comments

No Known Activations