INDEX

Explanations

terms related to knowledge and expertise

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 mukaan

-0.54

 automatiques

-0.52

 capables

-0.52

 vertes

-0.50

 Monfieur

-0.48

 wró

-0.45

 whoſe

-0.44

 nød

-0.43

 alimentaires

-0.43

POSITIVE LOGITS

########.

0.76

 '\\;'

0.75

 betweenstory

0.74

 незавершена

0.74

BufferException

0.73

IntoConstraints

0.73

webElementXpaths

0.70

 Roskov

0.69

stdc

0.68

 kaarangay

0.68

Activations Density 0.537%

terms related to knowledge and expertise

No Comments

No Known Activations