INDEX

Explanations

mentions of specific hospital names

oai_token-act-pair · gpt-3.5-turbo

references to hospitals and medical facilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 sheet

-0.86

outed

-0.75

 sheets

-0.74

heet

-0.69

 blur

-0.67

 moms

-0.65

 aspiring

-0.65

 literacy

-0.64

 silence

-0.62

artist

-0.62

POSITIVE LOGITS

 District

1.12

 Hotel

1.07

 Plaza

1.06

 Association

1.01

 Complex

0.98

 Parkway

0.97

 Simulator

0.97

 Partners

0.96

 Authority

0.95

 Trust

0.95

Activations Density 0.093%

mentions of specific hospital names

references to hospitals and medical facilities

No Comments

No Known Activations