INDEX

Explanations

negation expressions or conditions in programming contexts

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

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

ValueStyle

-0.84

RenderAtEndOf

-0.74

(!

-0.73

StoryboardSegue

-0.64

!):

-0.61

genheim

-0.60

(!

-0.59

makeText

-0.58

存于互联网档案馆

-0.57

romic

-0.57

POSITIVE LOGITS

 mera

0.30

Syntax

0.28

 Bonnie

0.27

ื่น

0.26

bundle

0.26

่วม

0.26

 calme

0.25

 solitario

0.25

 geográfica

0.25

prz

0.24

Activations Density 0.005%

negation expressions or conditions in programming contexts

No Comments

No Known Activations