INDEX

Explanations

logarithmic expressions and mathematical notations related to functions

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

 initComponents

-0.63

verwijspagina

-0.52

accio

-0.50

zköz

-0.48

uarts

-0.46

 Bintang

-0.46

RTLR

-0.46

 RSVP

-0.45

ReusableCell

-0.45

/*---

-0.44

POSITIVE LOGITS

WriteBarrier

0.53

MENAFN

0.43

Slf

0.43

InSection

0.42

ln

0.41

 hours

0.35

log

0.35

MessageOf

0.35

 logarithm

0.34

 logarithmic

0.34

Activations Density 0.065%

logarithmic expressions and mathematical notations related to functions

No Comments

No Known Activations