INDEX

Explanations

references to marking or labeling actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

edicated

-0.81

tenham

-0.80

 Montagu

-0.77

<tbody>

-0.71

katapos

-0.71

satunya

-0.71

bibinfo

-0.70

氓

-0.69

polation

-0.69

קישורים

-0.69

POSITIVE LOGITS

 Marks

1.99

 marks

1.88

 mark

1.84

 Mark

1.83

Marks

1.78

Mark

1.77

 MARKS

1.77

marks

1.73

 MARK

1.73

mark

1.71

Activations Density 0.109%

references to marking or labeling actions

No Comments

No Known Activations