INDEX

Explanations

references to notable figures in architecture and their associated works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 transférez

-0.52

 bait

-0.46

</thead>

-0.45

losed

-0.44

 mostrarán

-0.44

TagMode

-0.42

 CreateTagHelper

-0.42

ULOS

-0.42

pprint

-0.41

{?}

-0.40

POSITIVE LOGITS

 raiſ

0.78

 purpoſe

0.76

 himſelf

0.73

 Monfieur

0.72

 reaſon

0.70

########.

0.69

 ſtate

0.69

StructEnd

0.69

 ſta

0.68

 ſtand

0.68

Activations Density 0.244%

references to notable figures in architecture and their associated works

No Comments

No Known Activations