INDEX

Explanations

numerical information or dates related to historical events

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

NewUrlParser

-1.02

parsedMessage

-1.02

 utafitiHapana

-0.93

 تضيفلها

-0.93

 doubtnut

-0.86

ItemBackground

-0.85

 '\\;'

-0.84

tvguidetime

-0.81

SourceChecksum

-0.80

 تانيه

-0.80

POSITIVE LOGITS

0.56

<eos>

0.56

0.55

in

0.53

to

0.53

0.52

 part

0.51

↵

0.50

em

0.49

had

0.49

Activations Density 0.451%

numerical information or dates related to historical events

No Comments

No Known Activations