INDEX

Explanations

references to fictional characters and their associated transformations or abilities

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

########.

-0.59

transQ

-0.58

AndEndTag

-0.55

Rüyada

-0.54

 nahilalakip

-0.51

Chham

-0.50

Tikang

-0.49

majánló

-0.47

لينكات

-0.45

ніципалі

-0.45

POSITIVE LOGITS

 AssemblyTitle

0.41

͖

0.40

Portály

0.39

mobileqq

0.38

 nôtre

0.36

 ujednoznacz

0.36

 judíos

0.35

 katholischen

0.35

glTexCoord

0.35

locaust

0.35

Activations Density 1.037%

references to fictional characters and their associated transformations or abilities

No Comments

No Known Activations