INDEX

Explanations

locations and venues

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

before "in" that are location names

np_acts-logits-general · gemini-2.0-flash

places followed by "in"

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

at

-1.10

ParallelGroup

-0.83

 tại

-0.75

At

-0.72

At

-0.68

ẠI

-0.68

喺

-0.61

WebElementEntity

-0.59

protoimpl

-0.58

Personendaten

-0.57

POSITIVE LOGITS

 where

0.75

 correctes

0.63

where

0.59

PyExc

0.57

medriver

0.57

où

0.54

tvguidetime

0.54

 vestito

0.52

gameserver

0.52

 indoss

0.52

Activations Density 0.373%

locations and venues

before "in" that are location names

places followed by "in"

No Comments

No Known Activations