INDEX

Explanations

assertions of confirmation or denial regarding events or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

voix

-0.55

IContainer

-0.54

nEnter

-0.54

 tell

-0.53

 урна

-0.52

worn

-0.52

MessageTagHelper

-0.52

CHM

-0.52

stuk

-0.52

уза

-0.52

POSITIVE LOGITS

 confirmed

1.82

 demonstrated

1.46

 stated

1.44

confirmed

1.44

 revealed

1.39

 Confirmed

1.38

 indicated

1.37

 announced

1.28

 acknowledged

1.27

 affirmed

1.26

Activations Density 0.334%

assertions of confirmation or denial regarding events or statements

No Comments

No Known Activations