INDEX

Explanations

references to typical human experiences and limitations

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

出版年

-0.58

brainly

-0.49

-0.48

申し上げます

-0.47

inted

-0.43

 фак

-0.42

shadowColor

-0.42

 ANCHE

-0.41

ніше

-0.40

 latter

-0.40

POSITIVE LOGITS

CloseOperation

1.11

 autorytatywna

0.86

 typical

0.86

 Paglinawan

0.84

klart

0.81

 typique

0.76

 Савезне

0.75

DebuggerNonUser

0.75

typical

0.74

 típica

0.74

Activations Density 0.314%

references to typical human experiences and limitations

No Comments

No Known Activations