INDEX

Explanations

references to scenes in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/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.0.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

tel

-0.55

eng

-0.52

aff

-0.49

 meta

-0.48

DM

-0.47

Len

-0.46

 differentiation

-0.45

bou

-0.45

 form

-0.44

soc

-0.44

POSITIVE LOGITS

Personendaten

0.74

 resourceCulture

0.58

 Gelegenheit

0.57

 Szene

0.57

 autorytatywna

0.57

 étoit

0.54

IndentedString

0.52

 okaza

0.52

 escenas

0.51

 étoient

0.50

Activations Density 0.276%

references to scenes in various contexts

No Comments

No Known Activations