INDEX

Explanations

conditional phrases indicating applicability or necessity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 nobody

-0.56

 Nobody

-0.52

 flesta

-0.49

nobody

-0.49

jstor

-0.47

 Everybody

-0.46

 Geheimnis

-0.46

 adesso

-0.45

ErrUnexpectedEOF

-0.45

 everybody

-0.45

POSITIVE LOGITS

 الدولى

0.79

iastes

0.74

SourceChecksum

0.72

 EconPapers

0.70

PerformLayout

0.66

SCS

0.63

saraba

0.63

asiun

0.62

 betweenstory

0.62

XmlAccessorType

0.62

Activations Density 0.193%

conditional phrases indicating applicability or necessity

No Comments

No Known Activations