INDEX

Explanations

references to individuals and their actions or statements in a text

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Heere

-0.53

writeField

-0.48

 myſelf

-0.47

<bos>

-0.47

 caufe

-0.47

nextElement

-0.47

 mxArray

-0.47

OptionsMenu

-0.46

siębior

-0.46

 occaf

-0.46

POSITIVE LOGITS

]--;

0.62

出版年

0.57

новништво

0.57

tagHelperRunner

0.56

slidesPer

0.54

arrière

0.53

]++;

0.53

__*/

0.53

 onBind

0.53

 insuffisamment

0.53

Activations Density 0.564%

references to individuals and their actions or statements in a text

No Comments

No Known Activations