INDEX

Explanations

phrases related to connections or associations between individuals or groups

oai_token-act-pair · gpt-3.5-turbo

references to associations or connections between individuals or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

hma

-0.66

Station

-0.65

xious

-0.63

oplan

-0.62

Ħ¢

-0.61

afa

-0.60

Ath

-0.60

},{"

-0.60

 Atmosp

-0.60

 Hurricane

-0.60

POSITIVE LOGITS

 ties

1.46

tie

1.03

 tied

0.90

tie

0.87

 links

0.82

 knit

0.81

hips

0.80

hig

0.79

 connected

0.77

 tying

0.76

Activations Density 0.008%

phrases related to connections or associations between individuals or groups

references to associations or connections between individuals or entities

No Comments

No Known Activations