INDEX

Explanations

elements related to legal terminology and expressions of liability

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

Code snippets or license agreements

np_acts-logits-general · gemini-2.0-flash

licensed under

np_acts-logits-general · gemini-2.5-flash-lite

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

henge

-0.69

enderror

-0.67

 يتيمه

-0.66

 CURIAM

-0.65

igue

-0.62

angerie

-0.61



-0.61

argout

-0.60

SOUNDBITE

-0.60

 rospy

-0.59

POSITIVE LOGITS

itemize

0.90

usa

0.54

·

0.49

 reduce

0.48

 Schulte

0.48

 dashes

0.47

verse

0.47

otter

0.47

 Britton

0.47

 reduction

0.46

Activations Density 0.119%

elements related to legal terminology and expressions of liability

Code snippets or license agreements

licensed under

No Comments

No Known Activations