INDEX

Explanations

phrases that indicate inclusion or specification of items or examples

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 betweenstory

-0.46

msgSender

-0.41

toThrow

-0.38

initComponents

-0.37

 raiſ

-0.36

 ferait

-0.36

Reprodução

-0.36

 feroit

-0.36

PostInfinity

-0.35

GEBURTSDATUM

-0.35

POSITIVE LOGITS

 Types

0.55

 types

0.55

non

0.51

 kinds

0.51

 subtypes

0.50

 classic

0.50

 Rolf

0.50

 odious

0.50

ypes

0.50

 fieldNum

0.50

Activations Density 0.086%

phrases that indicate inclusion or specification of items or examples

No Comments

No Known Activations