INDEX

Explanations

phrases related to injuries and medical conditions

oai_token-act-pair · gpt-3.5-turbo

instances of injuries or fatalities reported in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 challeng

-0.93

 tempt

-0.89

 stagn

-0.84

 boycot

-0.81

 monopol

-0.81

 persu

-0.81

 subtly

-0.80

 renegoti

-0.79

 sustainable

-0.78

 enriched

-0.76

POSITIVE LOGITS

 Investigators

1.58

 Authorities

1.51

 Witnesses

1.41

 Officials

1.37

 Prosecutors

1.29

 Charges

1.26

 Officers

1.24

 Forensic

1.24

Investigators

1.22

 According

1.19

Activations Density 0.283%

phrases related to injuries and medical conditions

instances of injuries or fatalities reported in a narrative context

No Comments

No Known Activations