INDEX

Explanations

phrases indicating inclusion or necessity

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 arşivlendi

-0.63

 prece

-0.56

 استنادى

-0.50

vode

-0.45

stras

-0.45

러

-0.45

 matel

-0.45

rescence

-0.45

vertre

-0.45

 environment

-0.44

POSITIVE LOGITS

 CreateTagHelper

0.98

parsedMessage

0.68

 scattata

0.68

хьтан

0.66

StructEnd

0.63

copyWith

0.61

LEGGI

0.61

transQ

0.60

Pozdrawiam

0.59

enegger

0.57

Activations Density 0.039%

phrases indicating inclusion or necessity

No Comments

No Known Activations