INDEX

Explanations

references to official roles or titles within a hierarchy

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

encodeWith

-0.58

юрпри

-0.58

</tfoot>

-0.53

værende

-0.53

__(/*!

-0.52

itah

-0.52

معلومات

-0.51

ESTE

-0.49

WEBPACK

-0.49

 sekal

-0.49

POSITIVE LOGITS

 then

2.74

then

2.32

Then

2.27

 Then

2.27

 THEN

2.04

 puis

1.95

 سپس

1.90

 затем

1.88

 kemudian

1.87

 followed

1.85

Activations Density 0.577%

references to official roles or titles within a hierarchy

No Comments

No Known Activations