INDEX

Explanations

literals indicating prior events or repetitions

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

preceding "previous," "prior," "earlier," or "last."

np_acts-logits-general · gemini-2.0-flash

previous or prior events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

WireFormatLite

-0.68

 ISNI

-0.61

ValueStyle

-0.59

 InkWell

-0.58

TagMode

-0.57

 Signalez

-0.56

setVerticalGroup

-0.55

ulite

-0.54

featureID

-0.53

coltà

-0.49

POSITIVE LOGITS

 previous

4.30

previous

3.79

Previous

3.52

 Previous

3.50

 PREVIOUS

3.11

 предыду

2.98

 earlier

2.93

 prior

2.85

 past

2.75

PREVIOUS

2.70

Activations Density 1.316%

literals indicating prior events or repetitions

preceding "previous," "prior," "earlier," or "last."

previous or prior events

No Comments

No Known Activations

literals indicating prior events or repetitions

preceding "previous," "prior," "earlier," or "last."

previous or prior events

No Comments

No Known Activations