INDEX

Explanations

terms related to public health

oai_token-act-pair · gpt-3.5-turbo

references to public health-related topics

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pload

-0.74

coni

-0.71

Syl

-0.70

 Vander

-0.70

 shred

-0.68

 Claus

-0.65

 Hawth

-0.64

 Rouge

-0.63

âķĲ

-0.62

KER

-0.62

POSITIVE LOGITS

 advis

1.00

 care

0.96

 hazards

0.83

 emergencies

0.82

 practition

0.77

oppable

0.77

 professionals

0.77

iest

0.77

 oversight

0.77

aceutical

0.76

Activations Density 0.020%

terms related to public health

references to public health-related topics

No Comments

No Known Activations