INDEX

Explanations

terms related to function and functionality in biological or experimental contexts

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

"Functional" followed by a related term

np_acts-logits-general · gemini-2.0-flash

functional or operational attributes

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 convidados

-0.63

 appunto

-0.52

 llorar

-0.51

 précédemment

-0.50

 déclar

-0.50

 confezione

-0.50

 oiseaux

-0.49

 reír

-0.48

sc

-0.48

POSITIVE LOGITS

^(@)

0.87

 myſelf

0.83

Efq

0.83

%)$

0.79

setVerticalGroup

0.76

BibitemShut

0.74

 ―――――

0.73

cai

0.72

 OFDb

0.72

 ་་

0.72

Activations Density 0.360%

terms related to function and functionality in biological or experimental contexts

"Functional" followed by a related term

functional or operational attributes

No Comments

No Known Activations