INDEX

Explanations

questions and expressions of confusion or inquiry

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 malheureusement

-0.56

 unfortunately

-0.55

 сожалению

-0.53

 purtroppo

-0.50

unfortunately

-0.49

/>";

-0.49

 Unfortunately

-0.47

）』

-0.46

Unfortunately

-0.45

 zade

-0.44

POSITIVE LOGITS

 surely

1.40

 Surely

1.39

Surely

1.36

 Shouldn

1.30

 przecież

1.22

Shouldn

1.21

Isn

1.11

难道

1.09

Isn

1.07

不就是

1.06

Activations Density 0.410%

questions and expressions of confusion or inquiry

No Comments

No Known Activations