INDEX

Explanations

locations or events associated with fairs

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Fair" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

OPLE

-0.71

 bottleneck

-0.69

 Uriel

-0.68

auri

-0.66

 heck

-0.64

 habitable

-0.60

 bracelet

-0.60

asive

-0.60

 extrad

-0.60

 hell

-0.59

POSITIVE LOGITS

grounds

1.44

banks

1.14

child

1.04

ground

1.01

fair

1.00

places

0.88

field

0.87

yt

0.83

bread

0.82

mont

0.80

Activations Density 0.013%

locations or events associated with fairs

occurrences of the word "Fair" in various contexts

No Comments

No Known Activations