INDEX

Explanations

terms related to locations and items hidden or stored within them

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 isInitialized

-0.59

parsedMessage

-0.55

riwal

-0.51

ParallelGroup

-0.51

 &___

-0.49

HostException

-0.48

}`)

-0.48

ագրություններ

-0.48

வத

-0.47

ArgsConstructor

-0.47

POSITIVE LOGITS

 drawer

0.89

 cupboard

0.83

 closet

0.72

 drawers

0.71

 possession

0.70

 trunk

0.65

 dresser

0.65

 cupboards

0.65

 cabinet

0.65

 freezer

0.63

Activations Density 0.319%

terms related to locations and items hidden or stored within them

No Comments

No Known Activations