INDEX

Explanations

instances of the word "A"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

Personendaten

-0.70

)");

-0.70

kháu

-0.67



-0.67

AllAfrica

-0.66

prepareStatement

-0.64

[]

-0.60

typeorm

-0.60

 Paglinawan

-0.58

⋙

-0.58

POSITIVE LOGITS

1.13

0.80

0.66

0.65

0.64

0.63

0.62

0.59

Activations Density 0.237%

instances of the word "A"

No Comments

No Known Activations