INDEX

Explanations

dates and times related to events

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

followed by punctuation or symbols

np_acts-logits-general · gemini-2.0-flash

dates, math, biology

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

 ModelExpression

-0.61

◀

-0.59

matchCondition

-0.57

chst

-0.56

noopener

-0.56

ktioner

-0.54

orations

-0.53

hatic

-0.53

 Roskov

-0.53

 affichés

-0.53

POSITIVE LOGITS

AddTagHelper

0.60

 للمعارف

0.59

Datuak

0.58

 ArrayAdapter

0.54

StoreMessageInfo

0.49

endregion

0.48

 honour

0.47

MemoryWarning

0.46

 nein

0.45

ViewImports

0.45

Activations Density 0.023%

dates and times related to events

followed by punctuation or symbols

dates, math, biology

No Comments

No Known Activations