INDEX

Explanations

references to research or inquiry

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

 发表于

-0.59

 gyhoeddwyd

-0.55

 चीज़ों

-0.54

flashdata

-0.52

apture

-0.52

 Soal

-0.51

 Deixe

-0.51

mbals

-0.50

WithIOException

-0.49

forRoot

-0.48

POSITIVE LOGITS

 googling

1.95

 google

1.91

 Google

1.84

 googled

1.73

 researching

1.66

Google

1.64

 research

1.61

 GOOGLE

1.56

google

1.53

 researched

1.51

Activations Density 0.504%

references to research or inquiry

No Comments

No Known Activations