INDEX

Explanations

references to the term "various."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Humb

-0.69

 XCTest

-0.68

That

-0.68

Breath

-0.68

DMD

-0.67

lessness

-0.66

chter

-0.66

 thought

-0.65

APL

-0.64

 Darm

-0.64

POSITIVE LOGITS

各样的

1.00

httphttps

1.00

لينكات

0.97

 Kraus

0.91

]';

0.87

 متعلقه

0.85

cellaneous

0.85

rivial

0.84

DataSetChanged

0.84

enuine

0.84

Activations Density 0.101%

references to the term "various."

No Comments

No Known Activations