INDEX

Explanations

scientific methodologies and comparisons within research studies

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

Efq

-1.10

 myſelf

-1.08

 himſelf

-1.01

ſelf

-1.01

 Jefus

-0.99

 houſe

-0.99

 purpoſe

-0.97

 Majefty

-0.96

 pleaſure

-0.92

 Monfieur

-0.92

POSITIVE LOGITS

—

0.57

zta

0.56

0.54

 kasarigan

0.54

its

0.53

---

0.51

ilid

0.49

Stu

0.48

CRETE

0.48

Activations Density 0.146%

scientific methodologies and comparisons within research studies

No Comments

No Known Activations