INDEX

Explanations

words related to cleanliness, hygiene, and sanitation

oai_token-act-pair · gpt-3.5-turbo

terms related to hygiene and sanitation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

doms

-0.78

inez

-0.76

PsyNetMessage

-0.74

NetMessage

-0.73

*/(

-0.70

gered

-0.69

peak

-0.69

ozy

-0.69

icts

-0.68

acular

-0.68

POSITIVE LOGITS

 hygiene

1.06

ufact

0.89

iencies

0.88

itary

0.88

 steril

0.87

 sanitation

0.84

 Paste

0.80

acco

0.79

san

0.78

 linen

0.78

Activations Density 0.029%

words related to cleanliness, hygiene, and sanitation

terms related to hygiene and sanitation

No Comments

No Known Activations