INDEX

Explanations

words related to tropical regions and weather

oai_token-act-pair · gpt-3.5-turbo

references to tropical environments and conditions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

avering

-0.95

DN

-0.84

VW

-0.80

Merit

-0.78

umbn

-0.77

ifice

-0.76

edy

-0.76

UGC

-0.76

adr

-0.75

baugh

-0.75

POSITIVE LOGITS

 tropical

1.02

 islands

0.91

 paradise

0.91

 island

0.88

 deforestation

0.85

 forests

0.84

 Tropical

0.84

 fruits

0.83

 vegetation

0.81

 forest

0.81

Activations Density 0.010%

words related to tropical regions and weather

references to tropical environments and conditions

No Comments

No Known Activations