INDEX

Explanations

specific indicative phrases and introductory elements that suggest context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 дописавши

-0.95

 utafitiHapana

-0.95

RetentionPolicy

-0.89

 ddelweddau

-0.86

Geplaatst

-0.85

saraba

-0.83

 nakalista

-0.81

 Meksiku

-0.79

PreInfinity

-0.79

Personendaten

-0.77

POSITIVE LOGITS

 distance

0.60

 within

0.50

 short

0.48

distance

0.46

FloatField

0.43

 across

0.41

Btu

0.41

 distancia

0.41

 Myles

0.41

 steps

0.40

Activations Density 0.083%

specific indicative phrases and introductory elements that suggest context

No Comments

No Known Activations