INDEX

Explanations

numerical values relating to historical events or dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

useNewUrlParser

-0.45

Autoritní

-0.41

 Administrativna

-0.40

上手

-0.39

bParam

-0.37

setDo

-0.36

AISSEE

-0.35

存于互联网档案馆

-0.35

chism

-0.35

flashdata

-0.35

POSITIVE LOGITS

MLLoader

0.58

SequentialGroup

0.55

CloseOperation

0.53

ponses

0.48

rungsseite

0.47

 candidates

0.46

 summaries

0.45

 فريبيس

0.45

[*]

0.43

 propOrder

0.43

Activations Density 0.801%

numerical values relating to historical events or dates

No Comments

No Known Activations