INDEX

Explanations

occurrences of variable or placeholder symbols, particularly in a programming or mathematical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

DispatchToProps

-0.52

 because

-0.50

because

-0.48

editary

-0.47

ρεί

-0.46

 sockaddr

-0.46

 padat

-0.46

 eiland

-0.46

است

-0.45

 dalamnya

-0.44

POSITIVE LOGITS

 BorderRadius

0.96

 שוליים

0.72

 indisponible

0.71

NameInMap

0.69

'])){

0.68

Personendaten

0.67

 bağlantılar

0.66

antMatchers

0.65

WriteBarrier

0.64

 muualla

0.63

Activations Density 0.331%

occurrences of variable or placeholder symbols, particularly in a programming or mathematical context

No Comments

No Known Activations