INDEX

Explanations

references to famous or notorious entities

oai_token-act-pair · gpt-3.5-turbo

references to well-known or notorious individuals or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

orthy

-0.85

ÄŁ

-0.83

atu

-0.80

redits

-0.78

AAAA

-0.76

thia

-0.76

cht

-0.74

ometers

-0.74

onis

-0.73

vere

-0.73

POSITIVE LOGITS

 beast

0.73

 Frenchman

0.73

 comeback

0.73

 trio

0.71

 Prometheus

0.70

Blu

0.70

 anti

0.69

duo

0.69

 wooden

0.69

"#

0.69

Activations Density 0.197%

references to famous or notorious entities

references to well-known or notorious individuals or entities

No Comments

No Known Activations