INDEX

Explanations

programming-related terms and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

<eos>

-0.55

Hyd

-0.51

 esser

-0.48

↵↵

-0.48

chus

-0.48

 živ

-0.46

Hyd

-0.46

 Hens

-0.45

hen

-0.44

Hudson

-0.43

POSITIVE LOGITS

Efq

0.99

 myſelf

0.96

 auffi

0.89

 ſte

0.83

 iſt

0.81

 CreateTagHelper

0.81

 becauſe

0.80

 whoſe

0.79

ſelf

0.79

 ſhe

0.77

Activations Density 0.254%

programming-related terms and concepts

No Comments

No Known Activations