INDEX

Explanations

references to specific numerical values and letters, particularly in a structured format like code or data entries

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

-0.51

-0.50

-0.49

-0.48

↵

-0.47

-0.46

-0.42

ام

-0.41

asan

-0.41

POSITIVE LOGITS

 betweenstory

1.33

 ExecuteAsync

1.01

 OFDb

1.01

 houſe

0.91

contentLoaded

0.91

 Houſe

0.89

 Majefty

0.88

UserScript

0.87

Efq

0.86

sidemargin

0.86

Activations Density 0.634%

references to specific numerical values and letters, particularly in a structured format like code or data entries

No Comments

No Known Activations