INDEX

Explanations

references to independent entities or individuals

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

 kaarangay

-0.59

 CreateTagHelper

-0.52

WHEREAS

-0.52

 RequestMethod

-0.50

tió

-0.48

gyz

-0.48

unnitel

-0.48

StoryboardSegue

-0.48

gæ

-0.47

 ComVisible

-0.47

POSITIVE LOGITS

 Independent

0.89

Independent

0.84

 vone

0.83

自主

0.82

=?";

0.81

 Indep

0.78

']))

0.76

Independence

0.74

independent

0.73

Isolate

0.73

Activations Density 0.122%

references to independent entities or individuals

No Comments

No Known Activations