INDEX

Explanations

references to research studies and their results

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

 '\\;'

-0.82

bibfield

-0.76

bibinfo

-0.75

 utafitiHapana

-0.72

NewUrlParser

-0.71

 mxArray

-0.69

 فريبيس

-0.66

存于互联网档案馆

-0.65

/\.

-0.64

BibitemShut

-0.63

POSITIVE LOGITS

 thus

2.62

so

2.15

thus

1.98

Thus

1.88

 Thus

1.80

so

1.55

So

1.53

 sejauh

1.48

So

1.45

 bisher

1.43

Activations Density 0.582%

references to research studies and their results

No Comments

No Known Activations