INDEX

Explanations

terms related to various medical conditions and health issues

oai_token-act-pair · gpt-3.5-turbo

terms related to negative health conditions and issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Alphabet

-0.73

Wem

-0.72

eworld

-0.72

cale

-0.71

 Pace

-0.70

ertodd

-0.69

riel

-0.68

DonaldTrump

-0.68

 DeVos

-0.67

 Bezos

-0.66

POSITIVE LOGITS

 failure

1.33

 instability

1.33

 malfunction

1.28

 exhaustion

1.24

 collapse

1.24

 shortages

1.23

 failures

1.21

 dysfunction

1.20

 deterioration

1.20

 starvation

1.19

Activations Density 0.528%

terms related to various medical conditions and health issues

terms related to negative health conditions and issues

No Comments

No Known Activations