INDEX

Explanations

mathematical expressions and symbols, particularly involving operations and variables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

RTDA

-0.51

 cipolla

-0.49

 vorstellen

-0.48

screen

-0.47

])]

-0.45

етки

-0.45

softc

-0.45

textArea

-0.43

EOR

-0.42

 estu

-0.42

POSITIVE LOGITS

 فريبيس

0.92

 EconPapers

0.80

 myſelf

0.79

NameInMap

0.79

ſelves

0.79

enumi

0.77

 purpoſe

0.76

tagHelperRunner

0.76

 itſelf

0.76

abetes

0.76

Activations Density 0.615%

mathematical expressions and symbols, particularly involving operations and variables

No Comments

No Known Activations