INDEX

Explanations

correlations or links between different factors or variables

oai_token-act-pair · gpt-3.5-turbo

phrases that depict correlations or relationships between two variables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Company

-0.80

nw

-0.77

eez

-0.75

 Vaugh

-0.73

Reply

-0.72

liga

-0.71

isans

-0.70

Conn

-0.70

UGH

-0.68

BuyableInstoreAndOnline

-0.67

POSITIVE LOGITS

 outcomes

1.10

 susceptibility

1.03

 propensity

0.91

 socioeconomic

0.87

 wellbeing

0.86

 obesity

0.86

 incidence

0.85

 initiation

0.84

 cognitive

0.83

 mortality

0.81

Activations Density 0.162%

correlations or links between different factors or variables

phrases that depict correlations or relationships between two variables

No Comments

No Known Activations