INDEX

Explanations

affirmative statements or expressions of belief in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 архивлан

-0.65

rungsseite

-0.56

<bos>

-0.54

Autoritní

-0.54

Advertisement

-0.53

 <<<<<<<<<<<<<<

-0.52

遞

-0.50

 guessed

-0.48

 prioritized

-0.47

 Loving

-0.47

POSITIVE LOGITS

findpost

0.66

AccessorTable

0.57

AnimationsModule

0.56

 tris

0.56

GIVEREF

0.56

]-->

0.55

mallows

0.55

 Autorizaciones

0.55

concern

0.54

 onCreateView

0.54

Activations Density 0.230%

affirmative statements or expressions of belief in various contexts

No Comments

No Known Activations