INDEX

Explanations

locations or places

oai_token-act-pair · gpt-3.5-turbo

references to specific geographic locations or cities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

thood

-0.87

oldemort

-0.82

requires

-0.81

utics

-0.79

DragonMagazine

-0.78

lain

-0.78

rss

-0.77

uden

-0.76

netflix

-0.76

*/(

-0.75

POSITIVE LOGITS

 Institute

0.90

 skyline

0.84

 Gazette

0.83

 edition

0.82

 version

0.81

 Observer

0.80

 Police

0.79

 Herald

0.78

 Bureau

0.78

 Tribune

0.78

Activations Density 0.237%

locations or places

references to specific geographic locations or cities

No Comments

No Known Activations