INDEX

Explanations

proper nouns, particularly place names and related identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Zeneca

-0.82

hljs

-0.74

ientôt

-0.67

 OFDb

-0.67

FormTagHelper

-0.66

ArrowToggle

-0.66

MIDDLEWARE

-0.66

titleMargin

-0.66

floxacin

-0.65

انجليز

-0.65

POSITIVE LOGITS

Билгалдахарш

0.58

Koordinaten

0.52

 Kalt

0.51

IMC

0.49

Border

0.47

expandindo

0.47

 blast

0.47

 Linton

0.47

faro

0.46

 Examin

0.46

Activations Density 0.345%

proper nouns, particularly place names and related identifiers

No Comments

No Known Activations