INDEX

Explanations

conditional or normative phrases indicating obligation or expectation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

++]=

-0.55

ierungen

-0.52

 resultCode

-0.52

vail

-0.52

addGap

-0.51

.$.

-0.51

립

-0.51

 المعيارى

-0.51

вто

-0.51

olars

-0.50

POSITIVE LOGITS

harusnya

0.84

 Shouldn

0.80

Shouldn

0.76

 seharusnya

0.75

 normalement

0.74

should

0.73

 powinien

0.72

 powinny

0.70

Efq

0.69

 shouldBe

0.69

Activations Density 0.212%

conditional or normative phrases indicating obligation or expectation

No Comments

No Known Activations