INDEX

Explanations

specific proper nouns and key terms related to various topics, including people and scientific concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Diweddarwch

-0.52

writeFieldEnd

-0.51

 tartalomajánló

-0.50

 StringTokenizer

-0.47

EndInit

-0.46

principalColumn

-0.46

HostException

-0.44

GTCX

-0.44

 pleaſure

-0.43

RenderAtEndOf

-0.42

POSITIVE LOGITS

Autoritní

0.50

 للمعارف

0.50

 odkazy

0.49

rungsseite

0.46

 infância

0.45

Sklici

0.44

Kaynakça

0.44

 otomatig

0.42

 Pardo

0.40

 HasFactory

0.40

Activations Density 3.347%

specific proper nouns and key terms related to various topics, including people and scientific concepts

No Comments

No Known Activations