INDEX

Explanations

sentences with references to programming, function usage, or coding concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 („

-0.71

 (‘

-0.67

 (“

-0.63

(«

-0.53

„

-0.51

("

-0.50

 “¿

-0.49

 “…

-0.49

 “(

-0.49

‘

-0.48

POSITIVE LOGITS

uh

1.00

um

0.85

parsedMessage

0.80

Uh

0.74

Um

0.74

,))

0.74

 yeah

0.70

 Okay

0.70

SourceChecksum

0.67

//});

0.66

Activations Density 0.681%

sentences with references to programming, function usage, or coding concepts

No Comments

No Known Activations