INDEX

Explanations

references to government entities or official offices

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

éndolo

-0.54

astify

-0.52

ὴ

-0.51

!("{

-0.50

󠁢

-0.50

PRNewswire

-0.50

</thead>

-0.49

irtschaft

-0.49

 skład

-0.48

 tiên

-0.47

POSITIVE LOGITS

expandindo

0.61

principalColumn

0.57

JsonPropertyName

0.56

★

0.55

nteral

0.55

Билгалдахарш

0.54

0.53

IQR

0.52

own

0.52

 ObjectParameter

0.52

Activations Density 0.191%

references to government entities or official offices

No Comments

No Known Activations