INDEX

Explanations

programming constructs and variable declarations

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

PreferredItem

-0.94

 pleaſure

-0.75

 вікі

-0.74

 Majefty

-0.72

 resourceCulture

-0.72

 myſelf

-0.71

 سكانية

-0.70

Kjelder

-0.69

 ―――――

-0.68

 NUKAT

-0.68

POSITIVE LOGITS

Son

0.47

oznam

0.43

osaurus

0.42

ständige

0.40

最快更新

0.40

tored

0.40

 procesamiento

0.39

 anaknya

0.38

son

0.38

Activations Density 0.671%

programming constructs and variable declarations

No Comments

No Known Activations