INDEX

Explanations

references to processes involving washing and cleaning in scientific or instructional contexts

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

Datuak

-0.59

 Autónoma

-0.51

atchewan

-0.50

ParallelGroup

-0.49

spoken

-0.47

paced

-0.47

thaf

-0.47

odacty

-0.47

 zoning

-0.46

sibilità

-0.46

POSITIVE LOGITS

 thoroughly

0.92

 extensively

0.72

 liberally

0.72

 adecuadamente

0.71

 lightly

0.70

 heavily

0.70

 meticulously

0.68

protoc

0.68

MethodManager

0.68

 appropriately

0.67

Activations Density 0.334%

references to processes involving washing and cleaning in scientific or instructional contexts

No Comments

No Known Activations