INDEX

Explanations

sections of text that indicate a starting point for discussion or analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

WithIOException

-0.78

 Paglinawan

-0.73

EDEFAULT

-0.73

حياتها

-0.70

حياته

-0.65

WireFormatLite

-0.63

 שוליים

-0.63

IsContent

-0.62

ConstraintMaker

-0.62

 médicaux

-0.61

POSITIVE LOGITS

↵↵

0.76

<eos>

0.72

ณ

0.51

toplas

0.50

↵

0.50

 betweenstory

0.47

qvarna

0.47

APORE

0.46

us

0.45

soi

0.45

Activations Density 0.125%

sections of text that indicate a starting point for discussion or analysis

No Comments

No Known Activations