INDEX

Explanations

terms related to identity verification and personal documentation

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

хьтан

-0.60

fjspx

-0.57

]][

-0.52



-0.52

 Enlightenment

-0.51

sidemargin

-0.51

 onPostExecute

-0.50

):-

-0.50

>`;

-0.50

}}}}

-0.49

POSITIVE LOGITS

 flesta

0.75

 själva

0.67

ammans

0.62

 that

0.59

 mourut

0.58

를

0.58

ViewImports

0.58

IsContent

0.57

ături

0.56

가

0.55

Activations Density 0.058%

terms related to identity verification and personal documentation

No Comments

No Known Activations