INDEX

Explanations

language about research surveys and rewards

oai_token-act-pair · gemini-2.0-flash

rewards and consequences

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 reward

-2.39

 Reward

-2.16

 rewards

-2.14

Reward

-2.06

reward

-2.03

 rewarded

-1.93

 Rewards

-1.88

rewards

-1.75

Rewards

-1.74

 rewarding

-1.68

POSITIVE LOGITS

VersionUID

0.60

 հղումներ

0.51

]=>

0.45

URLException

0.43

stringstream

0.42

 Heer

0.40

Искәрмәләр

0.40

oa̍t

0.40

bable

0.40

Française

0.40

Activations Density 1.148%

language about research surveys and rewards

rewards and consequences

No Comments

No Known Activations