INDEX

Explanations

references to visitors or guests

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 &___

-0.83

 devriez

-0.83

="#"><

-0.79

ьаж

-0.78

 casó

-0.77

NameInMap

-0.76

 BorderRadius

-0.74

 devrez

-0.74

endpush

-0.71

Vidite

-0.70

POSITIVE LOGITS

 visitors

3.07

 Visitors

2.94

 visitor

2.79

Visitors

2.74

visitors

2.58

 Visitor

2.55

visitor

2.35

Visitor

2.27

 Besucher

1.84

 visiteurs

1.70

Activations Density 0.067%

references to visitors or guests

No Comments

No Known Activations