INDEX

Explanations

queries and requests for clarification or assistance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

ADVERT

-0.43

 Punj

-0.40

then

-0.38

undu

-0.38

End

-0.36

 conse

-0.35

present

-0.35

paris

-0.34

ividu

-0.34

 addi

-0.33

POSITIVE LOGITS

 EconPapers

1.06

AndEndTag

1.03

adpleegd

0.81

 дописавши

0.79

RectangleBorder

0.78

ValueStyle

0.78

setViewportView

0.77

 unknownFields

0.76

SequentialGroup

0.76

 nahilalakip

0.75

Activations Density 0.598%

queries and requests for clarification or assistance

No Comments

No Known Activations