INDEX

Explanations

references to YouTube links and video content

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

YouTube links

np_acts-logits-general · gemini-2.0-flash

don’t watch

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

MessageTagHelper

-0.81

 ModelExpression

-0.80

WebElementEntity

-0.78

 ExecuteAsync

-0.78

mybatisplus

-0.77

VolleyError

-0.75

rungsseite

-0.74

ẫu

-0.74

-0.73

новниш

-0.71

POSITIVE LOGITS

watch

0.73

 watch

0.66

feature

0.59

list

0.57

 Watch

0.53

 list

0.49

Watch

0.49

Feature

0.47

 feature

0.46

 user

0.45

Activations Density 0.086%

references to YouTube links and video content

YouTube links

don’t watch

No Comments

No Known Activations