INDEX

Explanations

references to programming and function calls in code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ỡng

-0.48

"]="

-0.44

逆に

-0.44

()<<

-0.43

however

-0.42

 however

-0.42

}}$.

-0.41

]<<

-0.40

",@"

-0.40

sique

-0.39

POSITIVE LOGITS

==

1.61

===

1.23

==

1.05

 equals

1.00

!=

0.98

 coincides

0.97

 isEqualToString

0.95

()==

0.92

 coincide

0.90

]==

0.89

Activations Density 0.244%

references to programming and function calls in code snippets

No Comments

No Known Activations