INDEX

Explanations

specific structured formats or patterns within textual data, likely related to mathematical or logical expressions

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

 betweenstory

-0.83

دانشنامهٔ

-0.64

HasForeignKey

-0.63

ViewImports

-0.63

 otomatig

-0.53

transQ

-0.53

таратура

-0.52

 &___

-0.52

 "$@"

-0.51

">';

-0.50

POSITIVE LOGITS

AnchorStyles

0.63

 CURIAM

0.62

 <<<<<<<<<<<<<<

0.62

InputBorder

0.61

 also

0.58

SupportActionBar

0.58

ispiele

0.57

BagConstraints

0.54

<bos>

0.54

ValueStyle

0.53

Activations Density 0.058%

specific structured formats or patterns within textual data, likely related to mathematical or logical expressions

No Comments

No Known Activations