INDEX

Explanations

references to specific classifications or categorizations in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 Haga

-0.74

 للاسماء

-0.71

']}

-0.69

)]:

-0.68

Sve

-0.67

 impres

-0.67

')}

-0.67

')]

-0.65

 Pech

-0.64

:')

-0.64

POSITIVE LOGITS

II

3.29

II

3.05

III

2.31

III

2.22

Ⅱ

1.89

ii

1.88

IIA

1.85

Ii

1.67

VII

1.66

IIII

1.60

Activations Density 0.073%

references to specific classifications or categorizations in scientific contexts

No Comments

No Known Activations