INDEX

Explanations

aspects of personal conversation and interaction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 venons

-0.44

**)

-0.43

stdc

-0.41

 diría

-0.40

 بدان

-0.40

 stanie

-0.40

bilir

-0.40

CDD

-0.39

fromCharCode

-0.39

 wydaje

-0.39

POSITIVE LOGITS

 betweenstory

0.54

adaptiveStyles

0.50

oredCriteria

0.48

PreInfinity

0.48

tinyos

0.47

 kaarangay

0.46

NameInMap

0.46



0.46

Cyfarwyddwr

0.45

 Numerade

0.43

Activations Density 0.587%

aspects of personal conversation and interaction

No Comments

No Known Activations