INDEX

Explanations

references to significant moments, events, or entities that provoke a sense of nostalgia or emphasize distinct characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ِّف

-0.66

 Roskov

-0.62

 wireType

-0.62

quiel

-0.60

Controllo

-0.59

createCell

-0.58

setVerticalGroup

-0.56

 مشين

-0.56

PyTuple

-0.56

aarrggbb

-0.55

POSITIVE LOGITS

AddRange

0.49

 like

0.49

 kind

0.47

 Partagez

0.45

lainen

0.45

的那种

0.44

 kiểu

0.44

 extérieures

0.43

 redenen

0.43

atihan

0.42

Activations Density 0.135%

references to significant moments, events, or entities that provoke a sense of nostalgia or emphasize distinct characteristics

No Comments

No Known Activations