INDEX

Explanations

descriptors indicating quality and specificity in products or services

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

PreInfinity

-0.65

 يتيمه

-0.60

 betweenstory

-0.58

ロウィン

-0.57

Geplaatst

-0.57

LookAnd

-0.54

 للاسماء

-0.54

abestanden

-0.54

RTEE

-0.54

OGND

-0.53

POSITIVE LOGITS

 solutions

0.49

 administration

0.42

 Faithful

0.40

 efficient

0.38

 integrated

0.37

 support

0.36

 meaningful

0.36

 administered

0.36

 complex

0.35

 services

0.35

Activations Density 0.026%

descriptors indicating quality and specificity in products or services

No Comments

No Known Activations