INDEX

Explanations

instances of the word "spot" in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 متعلقه

-0.78

lisi

-0.77

 Dene

-0.75

complexContent

-0.74

THISDAY

-0.72

ölkerung

-0.72

CLS

-0.71

ogeneous

-0.71

 Schlegel

-0.71

pédie

-0.70

POSITIVE LOGITS

 spot

1.07

 Spot

0.95

spot

0.88

 SPOT

0.87

staun

0.87

Spot

0.86

 Squad

0.85

 paſſ

0.84

 Spots

0.83

 Jefus

0.81

Activations Density 0.069%

instances of the word "spot" in the text

No Comments

No Known Activations