INDEX

Explanations

conversational expressions and thoughts shared in dialogue

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Audit

-0.30

 Sieben

-0.29

 data

-0.29

roek

-0.28

Życiorys

-0.27

sihan

-0.26

 audit

-0.26

 cases

-0.26

при

-0.26

ほど

-0.26

POSITIVE LOGITS

ConstraintMaker

0.84

SequentialGroup

0.77

MLLoader

0.73

AndEndTag

0.73

 resourceCulture

0.71

TagMode

0.70

 Italijani

0.69

 ProtoMessage

0.66

 Anſ

0.64

makeText

0.63

Activations Density 0.214%

conversational expressions and thoughts shared in dialogue

No Comments

No Known Activations