INDEX

Explanations

language-related constructs and operations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 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

 ostavi

-0.49

uté

-0.49

ensement

-0.47

Примітки

-0.45

 verrez

-0.45

Tazama

-0.44

urable

-0.44

foque

-0.44

mbing

-0.43

nities

-0.42

POSITIVE LOGITS

 want

2.96

want

2.75

 wanting

2.67

 Want

2.65

 wanted

2.62

 wants

2.61

 desire

2.51

Want

2.45

 WANT

2.31

wanted

2.24

Activations Density 0.625%

language-related constructs and operations

No Comments

No Known Activations