INDEX

Explanations

percentages and numbers related to various categories

oai_token-act-pair · gpt-3.5-turbo

references to numerical data or statistical information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RAW

-0.72

ful

-0.70

 alone

-0.67

PLA

-0.66

pedia

-0.63

smith

-0.63

æ³

-0.61

fully

-0.61

rade

-0.60

fy

-0.60

POSITIVE LOGITS

 populace

0.92

 country

0.88

 nation

0.88

 electorate

0.87

 population

0.84

 smallest

0.83

 workforce

0.83

 heaviest

0.82

 equation

0.78

 globe

0.77

Activations Density 0.106%

percentages and numbers related to various categories

references to numerical data or statistical information

No Comments

No Known Activations