INDEX

Explanations

numerical values expressed as percentages or measurements

oai_token-act-pair · gpt-3.5-turbo

punctuation symbols

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

 advis

-0.75

 salty

-0.71

 hostage

-0.68

 swim

-0.67

 braces

-0.63

 anomal

-0.63

 electr

-0.62

 ultras

-0.62

 beaut

-0.62

 architectural

-0.61

POSITIVE LOGITS

1.28

1.24

1.23

1.18

1.16

1.13

1.12

1.11

Activations Density 0.075%

numerical values expressed as percentages or measurements

punctuation symbols

No Comments

No Known Activations