INDEX

Explanations

abbreviations or acronyms of government agencies

oai_token-act-pair · gpt-3.5-turbo

instances of parentheses, indicating references to various organizations and agencies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 blot

-0.67

rhy

-0.67

 hinge

-0.63

 impe

-0.63

 untreated

-0.63

 earners

-0.62

bog

-0.62

 chalk

-0.61

lin

-0.60

 resur

-0.60

POSITIVE LOGITS

UGC

1.10

FBI

1.03

NYSE

1.02

UFC

1.01

AFP

1.00

CIA

1.00

NAS

0.99

ASC

0.99

NPR

0.98

ISO

0.98

Activations Density 0.045%

abbreviations or acronyms of government agencies

instances of parentheses, indicating references to various organizations and agencies

No Comments

No Known Activations