INDEX

Explanations

repeated elements or patterns in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

-0.81

-0.78

to

-0.60

of

-0.55

 Barbier

-0.54

-0.53

POSITIVE LOGITS

 Sarm

0.94

LK

0.88

Efq

0.85

MPR

0.83

PRD

0.82

 doubtnut

0.82

 bave

0.81

 itſelf

0.80

 Coss

0.79

 Shakspeare

0.78

Activations Density 1.830%

repeated elements or patterns in the text

No Comments

No Known Activations