INDEX

Explanations

accusations and denials in text

oai_token-act-pair · gpt-3.5-turbo

phrases related to denial of accusations

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

tnc

-0.81

 ausp

-0.72

ibaba

-0.70

Sensor

-0.69

odes

-0.68

Measure

-0.66

 ILCS

-0.65

rafted

-0.64

 mosqu

-0.63

 synergy

-0.63

POSITIVE LOGITS

 denies

1.43

 denied

1.38

 refuted

1.33

 deny

1.32

 retracted

1.30

 vehemently

1.25

 disav

1.24

 denying

1.21

 disputed

1.21

 contradicted

1.19

Activations Density 0.529%

accusations and denials in text

phrases related to denial of accusations

No Comments

No Known Activations