INDEX

Explanations

references to significant events or actions related to authority and governance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 виправивши

-0.69

CodedInputStream

-0.64

jstor

-0.59

msgTypes

-0.59

parsedMessage

-0.59

QMetaType

-0.56

存于互联网档案馆

-0.55

adə

-0.55

下载附件

-0.55

cerpts

-0.55

POSITIVE LOGITS

 thousands

3.01

 hundreds

2.88

thousands

2.61

hundreds

2.50

 Thousands

2.49

 millions

2.44

Thousands

2.43

 Hundreds

2.36

Hundreds

2.30

 tens

2.30

Activations Density 1.042%

references to significant events or actions related to authority and governance

No Comments

No Known Activations