INDEX

Explanations

words related to exploration and discovery

oai_token-act-pair · gpt-3.5-turbo

references to different fictional or conceptual worlds

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ippi

-0.98

sbm

-0.81

 Mehran

-0.80

aturday

-0.79

++++

-0.78

ifer

-0.77

etsk

-0.75

ividual

-0.72

inventoryQuantity

-0.71

oug

-0.70

POSITIVE LOGITS

liness

1.19

building

1.10

scape

0.95

view

0.91

wide

0.91

 domination

0.89

arium

0.88

views

0.85

builders

0.83

 inhabited

0.81

Activations Density 0.061%

words related to exploration and discovery

references to different fictional or conceptual worlds

No Comments

No Known Activations