INDEX

Explanations

terms related to credit

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

✨:

-0.85

osoba

-0.82

 beginnetje

-0.81

 nahilalakip

-0.81

expandindo

-0.80

enterOuterAlt

-0.79

endphp

-0.77

 transfieras

-0.76

談社

-0.76

WindowConstants

-0.75

POSITIVE LOGITS

 credit

3.47

 Credit

3.26

credit

3.01

Credit

3.01

 CREDIT

2.98

 credits

2.65

CREDIT

2.49

 Credits

2.40

credits

2.16

Credits

2.11

Activations Density 0.033%

terms related to credit

No Comments

No Known Activations