INDEX

Explanations

variations of the word "resulting."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

phosa

-0.62

Initializable

-0.57

 kokona

-0.54

们

-0.54

 NSCoder

-0.54

们的

-0.53

verständlich

-0.53

們

-0.53

ErrorListener

-0.52

 věci

-0.52

POSITIVE LOGITS

 resulting

3.25

resulting

2.99

 resultant

2.41

 ensuing

2.16

 consequent

1.69

 subsequent

1.59

 resulted

1.57

 résult

1.26

 arising

1.23

 Subsequent

1.15

Activations Density 0.121%

variations of the word "resulting."

No Comments

No Known Activations