INDEX

Explanations

numbers and statistical terms

oai_token-act-pair · gpt-3.5-turbo

references to statistical data and numbers

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

Interstitial

-0.82

mods

-0.71

 unsuccessfully

-0.70

CLA

-0.69

successfully

-0.67

 Deals

-0.66

emis

-0.64

sic

-0.64

 Contents

-0.64

umbing

-0.62

POSITIVE LOGITS

 graphs

1.03

 statistical

0.97

 statistic

0.92

 skewed

0.87

 averages

0.87

 probabilities

0.85

 projections

0.82

 statistics

0.81

 inflated

0.79

 percentages

0.78

Activations Density 0.367%

numbers and statistical terms

references to statistical data and numbers

No Comments

No Known Activations