INDEX

Explanations

active voicing classifying significant actions or events within a narrative

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

preceding "to"

np_acts-logits-general · gemini-2.0-flash

literally, almost, barely

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Roskov

-0.80

WebVitals

-0.58

 kuitenkin

-0.56

 kaarangay

-0.50

liš

-0.50

enderror

-0.50

 siis

-0.49

 kuiten

-0.48

الإنجليزية

-0.46

UVWXYZ

-0.45

POSITIVE LOGITS

 literally

0.97

 literalmente

0.94

 almost

0.90

 Literally

0.87

 litté

0.87

literally

0.86

almost

0.85

 barely

0.82

Literally

0.80

 practically

0.79

Activations Density 0.277%

active voicing classifying significant actions or events within a narrative

preceding "to"

literally, almost, barely

No Comments

No Known Activations