INDEX

Explanations

mathematical symbols and formatting elements

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

Efq

-1.59

 Monfieur

-1.54

 myſelf

-1.53

 Theſe

-1.48

 itſelf

-1.38

 iſt

-1.36

 Jefus

-1.35

 ―――――

-1.33

 ſeveral

-1.33

 Houſe

-1.33

POSITIVE LOGITS

1.08

0.74

$\

0.74

{\

0.73

<eos>

0.71

</tr>

0.70

...

0.69

<tr>

0.68

.\

0.68

Activations Density 0.100%

mathematical symbols and formatting elements

No Comments

No Known Activations