INDEX

Explanations

variations or distinctions in concepts or entities

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

starting with "diff" and its variations

np_acts-logits-general · gemini-2.0-flash

differ from

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

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ModelAdmin

-0.74

นี่

-0.57

ChildScrollView

-0.57

jsonwebtoken

-0.55

mazoo

-0.54

osidad

-0.54

setViewName

-0.54

OnTop

-0.54

 seyn

-0.53

DataURL

-0.53

POSITIVE LOGITS

differ

1.02

 Diff

1.00

Dif

1.00

Differ

0.99

DIF

0.97

Diff

0.96

 DIFFER

0.96

 diff

0.96

 differences

0.94

 Differences

0.93

Activations Density 0.222%

variations or distinctions in concepts or entities

starting with "diff" and its variations

differ from

No Comments

No Known Activations