INDEX

Explanations

references to data analysis and numerical values in research contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 myſelf

-1.02

 itſelf

-0.90

 purpoſe

-0.89

 houſe

-0.87

 <<<<<<<<<<<<<<

-0.87

 themſelves

-0.86

 ſeveral

-0.83

 ſmall

-0.82

 فريبيس

-0.81

 Jefus

-0.81

POSITIVE LOGITS

FetchType

0.51

＊

0.47

↵↵

0.44

Ty

0.44

or

0.44

rangle

0.42

Or

0.42

↵↵↵↵

0.41

Ty

0.41

or

0.41

Activations Density 0.927%

references to data analysis and numerical values in research contexts

No Comments

No Known Activations