INDEX

Explanations

phrases addressing the reader directly, particularly using "you."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

ảm

-0.47

honneur

-0.47

verständlich

-0.47

嫌疑

-0.47

rouvez

-0.45

postdata

-0.45

することも

-0.45

</thead>

-0.45

ApiModelProperty

-0.45

_("

-0.44

POSITIVE LOGITS

ask

0.88

 look

0.87

 asked

0.77

Ask

0.77

 LOOK

0.73

asked

0.73

 compare

0.72

Ask

0.72

 looked

0.71

 Look

0.71

Activations Density 0.122%

phrases addressing the reader directly, particularly using "you."

No Comments

No Known Activations