INDEX

Explanations

programming-related terminology and constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

دانشنامهٔ

-0.77

rungsseite

-0.76

 Theſe

-0.74

ismet

-0.69

 <>",

-0.67

 myſelf

-0.67

expandindo

-0.65

 Beſ

-0.64

 oprot

-0.64

 виправивши

-0.64

POSITIVE LOGITS

0.45

Hentet

0.44

0.43

pidou

0.42

0.39

nje

0.38

 nada

0.38

 HttpHeaders

0.37

 Busse

0.37

omitempty

0.37

Activations Density 1.251%

programming-related terminology and constructs

No Comments

No Known Activations