INDEX

Explanations

mentions of the White House

oai_token-act-pair · gpt-3.5-turbo

references to the White House

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

NetMessage

-0.83

Ô

-0.75

PsyNetMessage

-0.71

sin

-0.71

hra

-0.69

actionDate

-0.68

utic

-0.67

 ILCS

-0.66

eon

-0.66

REG

-0.66

POSITIVE LOGITS

 Counsel

0.95

 Office

0.91

 Correspond

0.91

 Situation

0.86

 counsel

0.84

 Depot

0.83

 Painter

0.82

 administrations

0.82

 Administration

0.78

 aides

0.77

Activations Density 0.030%

mentions of the White House

references to the White House

No Comments

No Known Activations