INDEX

Explanations

Twitter usernames

oai_token-act-pair · gpt-3.5-turbo

references to social media accounts, particularly Twitter handles

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

 ACTIONS

-0.97

 Scheme

-0.79

 Ninth

-0.76

CSI

-0.74

 Direction

-0.74

XVI

-0.74

FAC

-0.74

 Hearts

-0.74

 Index

-0.71

 Edge

-0.70

POSITIVE LOGITS

podcast

1.04

obal

1.01

0.97

yp

0.96

photos

0.95

kr

0.94

sth

0.93

anmar

0.92

aily

0.92

dn

0.92

Activations Density 0.137%

Twitter usernames

references to social media accounts, particularly Twitter handles

No Comments

No Known Activations