INDEX

Explanations

mentions of algorithms

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

queline

-0.86

jacke

-0.64

===

-0.64

हो

-0.64

Obl

-0.62

bA

-0.59

Cus

-0.58

 Shand

-0.58

 Brice

-0.58

POSITIVE LOGITS

 algorithm

2.01

 algorithms

1.98

 Algorithm

1.92

 Algorithms

1.87

algorithm

1.81

Algorithm

1.80

GORITHM

1.66

orithmic

1.58

算法

1.55

 algorit

1.54

Activations Density 0.083%

mentions of algorithms

No Comments

No Known Activations