INDEX

Explanations

output statements in programming code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

protoimpl

-0.80

 Amiga

-0.68

 Gabe

-0.67

yab

-0.66

 esters

-0.65

atisk

-0.64

댑

-0.64

SourceChecksum

-0.64

ClientSize

-0.63

Odd

-0.63

POSITIVE LOGITS

println

1.89

WriteLine

1.42

 println

1.41

AppendLine

1.09

writerow

0.94

)}.

0.79

."]

0.76

.")

0.75

Println

0.73

valueOf

0.72

Activations Density 0.027%

output statements in programming code

No Comments

No Known Activations