INDEX

Explanations

patterns of numerical values or sequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Roskov

-1.53

 ―――――

-1.51

webElementXpaths

-1.50

tagHelperRunner

-1.50

 myſelf

-1.47

تقاوى

-1.44

 doubtnut

-1.44

LookAnd

-1.41

 pleaſure

-1.38

 Jefus

-1.37

POSITIVE LOGITS

1.13

0.79

0.74

0.70

0.65

0.64

or

0.64

0.63

Activations Density 0.205%

patterns of numerical values or sequences

No Comments

No Known Activations