INDEX

Explanations

terms related to size and quantity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 SEDS

-0.50

 little

-0.47

自身

-0.46

 second

-0.46

 boca

-0.46

 lần

-0.45

St

-0.45

 juga

-0.45

EXPR

-0.44

avo

-0.44

POSITIVE LOGITS

 apiece

0.89

 saja

0.87

 تانيه

0.85

 виправивши

0.77

 IBOutlet

0.73

 مشين

0.70

AndEndTag

0.70

 sahaja

0.70

duy

0.69

extAlignment

0.69

Activations Density 0.231%

terms related to size and quantity

No Comments

No Known Activations