INDEX

Explanations

phrases related to time and events

oai_token-act-pair · gpt-3.5-turbo

phrases indicating uncertainty or exceptions in 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

GES

-0.74

rone

-0.68

anon

-0.66

 Constantin

-0.62

},{"

-0.62

Fra

-0.62

 Archdemon

-0.61

AME

-0.61

Benz

-0.61

Cause

-0.60

POSITIVE LOGITS

 hindsight

1.05

 bang

0.82

 exception

0.81

 caveat

0.77

 looming

0.74

 exceptions

0.72

 caveats

0.71

 democrat

0.71

draw

0.69

 twist

0.67

Activations Density 0.248%

phrases related to time and events

phrases indicating uncertainty or exceptions in contexts

No Comments

No Known Activations