INDEX

Explanations

mathematical expressions and notations, particularly those involving symbols and operators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Modern

-0.48

Modern

-0.43

Hi

-0.42

 modern

-0.42

Hi

-0.40

тек

-0.40

↵↵

-0.40

tagHelper

-0.40

 quần

-0.39

⋯

-0.38

POSITIVE LOGITS

 Chwiliwch

0.88

AndEndTag

0.81

ьаж

0.80

titleMargin

0.79

Referanser

0.78

TagMode

0.78

WithIOException

0.77

uxxxx

0.77

IntoConstraints

0.76

 kasarigan

0.76

Activations Density 1.056%

mathematical expressions and notations, particularly those involving symbols and operators

No Comments

No Known Activations