INDEX

Explanations

negative descriptors related to qualities or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

PyExc

-0.68

ății

-0.65

mybatisplus

-0.59

SharedDtor

-0.59

ParseTree

-0.58

EndProject

-0.56

JsonKey

-0.56

ᴥ

-0.55

eqn

-0.55

 takk

-0.55

POSITIVE LOGITS

bad

2.10

bad

1.92

Bad

1.83

Bad

1.80

 worse

1.52

BAD

1.50

BAD

1.37

 worst

1.30

 badly

1.27

 poor

1.26

Activations Density 0.105%

negative descriptors related to qualities or conditions

No Comments

No Known Activations