INDEX

Explanations

terms related to seasons and seasonal changes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 cardiaque

-0.68

 industriel

-0.67

 Taktlose

-0.64

 africains

-0.63

 Daß

-0.63

 Baccarat

-0.62

 gawas

-0.62

 réaliste

-0.61

 charité

-0.60

 acorde

-0.59

POSITIVE LOGITS

 season

1.09

 SEASON

0.81

 Season

0.80

SuppressLint

0.71

OGND

0.71

Season

0.67

season

0.64

aur

0.63

 saison

0.63

SEASON

0.61

Activations Density 0.280%

terms related to seasons and seasonal changes

No Comments

No Known Activations