INDEX

Explanations

names mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

references to people's names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

nuts

-0.71

 guiActiveUnfocused

-0.69

erker

-0.67

gif

-0.64

opian

-0.63

aunders

-0.63

yrinth

-0.62

 receptive

-0.61

psey

-0.60

Js

-0.60

POSITIVE LOGITS

plates

1.38

plate

1.34

 tags

0.89

tag

0.89

checked

0.88

 recognition

0.85

akes

0.84

 redacted

0.80

checks

0.80

paces

0.80

Activations Density 0.036%

names mentioned in the text

references to people's names

No Comments

No Known Activations