INDEX

Explanations

instances of the word "London" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 syno

-0.48

vok

-0.48

 énergé

-0.48

 butterknife

-0.47

 truths

-0.46

 aislamiento

-0.46

ρει

-0.46

Hav

-0.45

 isolamento

-0.45

zoo

-0.45

POSITIVE LOGITS

 متعلقه

0.87

</thead>

0.85

 London

0.82

underground

0.80

 CreateTagHelper

0.78

ⓧ

0.78

Underground

0.74

 Christmas

0.74

London

0.73

Personendaten

0.72

Activations Density 0.040%

instances of the word "London" in various contexts

No Comments

No Known Activations