INDEX

Explanations

content that is related to legal terminology or court proceedings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 excru

-0.55

 senti

-0.51

 Bort

-0.51

>>()

-0.49

що

-0.49

 bort

-0.49

Diwedd

-0.48

↵↵

-0.46

 internetowa

-0.46

 vernac

-0.46

POSITIVE LOGITS

enumi

1.21

tagHelperRunner

0.89

\{\\

0.85

enumii

0.85

+#+

0.83

 doInBackground

0.82

 تانيه

0.81

findpost

0.77

ⓧ

0.76

Lähteet

0.72

Activations Density 0.008%

content that is related to legal terminology or court proceedings

No Comments

No Known Activations