INDEX

Explanations

negative sentiments or expressions of disapproval

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ArrowToggle

-0.85

ſelves

-0.73

URIComponent

-0.72

 ―――――

-0.72

ſelf

-0.70

 myſelf

-0.69

 Theſe

-0.66

 Coleridge

-0.65

EndGlobal

-0.64

PyExc

-0.63

POSITIVE LOGITS

########.

0.63

0.50

holdet

0.48

__((

0.48

↵

0.48

 formatos

0.47

škas

0.46

 connexes

0.46

checkNotNull

0.46

invokeLater

0.45

Activations Density 0.129%

negative sentiments or expressions of disapproval

No Comments

No Known Activations