INDEX

Explanations

negative statements and their qualifiers

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

+:+

-0.69

BagLayout

-0.63

 préf

-0.58

 يتيمه

-0.55

/*

-0.55

 indisponible

-0.55

viewDidLoad

-0.54

شهاد

-0.54

 invokingState

-0.53

+#+#

-0.53

POSITIVE LOGITS

 matter

0.68

djangoproject

0.61

 detract

0.59

 externi

0.56

 compare

0.56

 excuse

0.56

 MATTER

0.55

 stop

0.54

 phase

0.53

 bode

0.52

Activations Density 0.207%

negative statements and their qualifiers

No Comments

No Known Activations