INDEX

Explanations

references to specific historical or geographical entities and terms associated with them

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 tartalomajánló

-0.57

Välislingid

-0.54

EndInit

-0.54

Посилання

-0.52

сылкі

-0.51

 kaarangay

-0.50

isContained

-0.49

談社

-0.47

GenerationType

-0.46

بوابة

-0.46

POSITIVE LOGITS

at

1.97

AT

1.92

ats

1.54

atnya

1.39

ATS

1.36

atk

1.31

att

1.30

AT

1.28

At

1.28

aten

1.27

Activations Density 1.016%

references to specific historical or geographical entities and terms associated with them

No Comments

No Known Activations