INDEX

Explanations

mathematical expressions and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 Dumnezeu

-0.52

 nationaux

-0.52

 tiet

-0.51

 semplicemente

-0.49

 pergunt

-0.48

 régional

-0.47

 Einstellung

-0.47

CAPTION

-0.46

 merely

-0.46

 eingestellt

-0.46

POSITIVE LOGITS

]^{-

0.74

parsedMessage

0.70

ⓧ

0.68

----</

0.66

)^{-

0.65

abetes

0.64

kuuta

0.63

invokeLater

0.61

 jsPsych

0.60

AddTagHelper

0.60

Activations Density 0.621%

mathematical expressions and symbols

No Comments

No Known Activations