INDEX

Explanations

different forms of the word "burn" and related concepts

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

rådet

-0.71

 EconPapers

-0.70

tabular

-0.70

nextSibling

-0.70

SuppressLint

-0.68

 jsonArray

-0.66

arrayOf

-0.63

 Fabio

-0.62

 fact

-0.62

CGRectMake

-0.61

POSITIVE LOGITS

 burn

2.23

 burns

2.17

 burning

2.08

 BURN

2.05

 burned

1.99

 Burning

1.99

 Burn

1.99

burning

1.93

burns

1.90

burn

1.86

Activations Density 0.072%

different forms of the word "burn" and related concepts

No Comments

No Known Activations