INDEX

Explanations

percentages or numerical data related terms

oai_token-act-pair · gpt-3.5-turbo

references to percentages and statistical changes related to growth or decline

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

Not in Any Lists

No Comments

Negative Logits

ãĥ¤

-0.69

lict

-0.66

vice

-0.62

ãĤ¦ãĤ¹

-0.60

quest

-0.59

liction

-0.58

rology

-0.55

values

-0.55

 grievances

-0.54

ãĥ¯ãĥ³

-0.54

POSITIVE LOGITS

 compared

0.83

bps

0.82

uary

0.78

 annually

0.77

Yo

0.72

 Shutterstock

0.69

ABV

0.68

 apiece

0.68

 during

0.67

 since

0.67

Activations Density 0.094%

percentages or numerical data related terms

references to percentages and statistical changes related to growth or decline

No Comments

No Known Activations