INDEX

Explanations

references to notable individuals or entities in various contexts, including mentions of achievements or impacts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 oprot

-0.64

 незавершена

-0.60

AutoScaleMode

-0.58

 viewType

-0.56

intenant

-0.56

AddressBook

-0.56

Geplaatst

-0.56

 ویکی‌پدی

-0.56

EndGlobalSection

-0.55

/=

-0.55

POSITIVE LOGITS

 even

4.51

even

3.90

Even

3.31

 sogar

3.29

 Even

3.19

 EVEN

3.15

 persino

3.10

 даже

3.04

 zelfs

2.93

 incluso

2.90

Activations Density 0.803%

references to notable individuals or entities in various contexts, including mentions of achievements or impacts

No Comments

No Known Activations