INDEX

Explanations

numeric milestones and significant achievements

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

发表于

-0.60

ânea

-0.55

OrNil

-0.52

']));

-0.51

 ujednoznacz

-0.50

])));

-0.50

aarrggbb

-0.50

protoc

-0.50

'}';

-0.49

LayoutPanel

-0.48

POSITIVE LOGITS

 mark

2.22

mark

1.71

 marks

1.61

marks

1.46

 MARK

1.44

Mark

1.41

 Mark

1.36

MARK

1.34

 marker

1.30

Marks

1.25

Activations Density 0.192%

numeric milestones and significant achievements

No Comments

No Known Activations