INDEX

Explanations

mentions of the name "Warren"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Warren"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ãĤ´ãĥ³

-0.87

pmwiki

-0.82

dayName

-0.79

unal

-0.75

netflix

-0.74

ãĤº

-0.74

bid

-0.73

odic

-0.70

 eleph

-0.69

kered

-0.68

POSITIVE LOGITS

 Buffett

1.23

 Warren

1.12

sburg

0.99

Warren

0.91

rade

0.90

 Farrell

0.86

 Davidson

0.80

ston

0.80

ers

0.79

 Sanders

0.76

Activations Density 0.006%

mentions of the name "Warren"

mentions of the name "Warren"

No Comments

No Known Activations