INDEX

Explanations

references to various forms of protective gear or equipment, particularly armor

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

 ComVisible

-0.80

ParallelGroup

-0.76

 Anaconda

-0.74

 Poto

-0.72

ährend

-0.70

 Sandro

-0.69

InteropServices

-0.68

PGC

-0.67

γγ

-0.67

 receipts

-0.67

POSITIVE LOGITS

 armour

0.84

 armor

0.84

 Knight

0.77

armor

0.75

Knights

0.73

 KNIGHT

0.70

 Knights

0.68

 Armor

0.67

 ddelweddau

0.65

warrior

0.65

Activations Density 0.142%

references to various forms of protective gear or equipment, particularly armor

No Comments

No Known Activations