INDEX

Explanations

numerical values associated with points or sections in a structured format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

<eos>

-0.59

']}

-0.51

"]}

-0.48

 kaarangay

-0.46

 masalah

-0.45

 problemas

-0.43

 procedere

-0.41

})).

-0.41

 regolare

-0.41

'].'

-0.40

POSITIVE LOGITS

 InputDecoration

1.16

AndEndTag

1.14

MemoryWarning

1.11

awtextra

1.07

WithIOException

0.97

findpost

0.96

帖最后由

0.94

 FetchType

0.92

 препратки

0.91

ImageContext

0.91

Activations Density 0.105%

numerical values associated with points or sections in a structured format

No Comments

No Known Activations