INDEX

Explanations

phrases related to spending time in different activities or locations

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the concept of spending time in various contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Editors

-0.76

iframe

-0.65

///

-0.64

.–

-0.64

erity

-0.64

Percent

-0.62

ulence

-0.61

pse

-0.61

 abound

-0.60

intendent

-0.60

POSITIVE LOGITS

 solitary

0.88

 contemplation

0.84

 solitude

0.83

anqu

0.77

 captivity

0.76

pless

0.73

oneliness

0.71

ORED

0.70

 Hamp

0.68

prison

0.67

Activations Density 0.146%

phrases related to spending time in different activities or locations

phrases indicating the concept of spending time in various contexts

No Known Activations