INDEX

Explanations

terms related to health organizations or departments

oai_token-act-pair · gpt-3.5-turbo

references to health organizations and health-related entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

maj

-0.83

 Logged

-0.73

Â¯

-0.65

 converter

-0.65

azaki

-0.64

=-=-

-0.64

*/(

-0.62

 vanquished

-0.62

 Brend

-0.62

umar

-0.61

POSITIVE LOGITS

 Care

1.07

Care

1.04

care

1.03

 Sciences

0.98

hazard

0.83

 Promotion

0.83

 care

0.83

osate

0.82

 Hazard

0.78

line

0.78

Activations Density 0.058%

terms related to health organizations or departments

references to health organizations and health-related entities

No Comments

No Known Activations