INDEX

Explanations

references to mathematical proofs and logical structures in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 utafitiHapana

-0.67

TagHelper

-0.63

 Infórmanos

-0.60

Externé

-0.57

BufferException

-0.54

(!__

-0.54

 Timoteo

-0.52

RenderAtEndOf

-0.52

}`}

-0.51

UnusedPrivate

-0.51

POSITIVE LOGITS

Datuak

0.74

rawDesc

0.58

mbols

0.55

unately

0.53

castic

0.52

kic

0.51

ometal

0.51

ktır

0.51

icrous

0.49

اعمال

0.49

Activations Density 0.971%

references to mathematical proofs and logical structures in a text

No Comments

No Known Activations