INDEX

Explanations

punctuation marks that signify the end of a statement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

AccessorTable

-0.61

 CreateTagHelper

-0.61

ölf

-0.60

kiwa

-0.57

AndEndTag

-0.56

principalTable

-0.56

 محفوظة

-0.54

LookAnd

-0.52

الحياه

-0.52

 TextAlign

-0.51

POSITIVE LOGITS

 Liability

0.55

 Transportation

0.54

 polymorph

0.51

webElementXpaths

0.49

Condition

0.49

ensi

0.48

oulos

0.47

 Wiseman

0.47

Transportation

0.46

поли

0.46

Activations Density 0.069%

punctuation marks that signify the end of a statement

No Comments

No Known Activations