INDEX

Explanations

legal or regulatory terms and actions

oai_token-act-pair · gpt-3.5-turbo

terms related to eligibility, restrictions, and regulatory concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

.</

-0.55

.''.

-0.54

Oxy

-0.53

.).

-0.52

 Commun

-0.49

.-

-0.49

etc

-0.48

 Scientific

-0.48

Amb

-0.46

POSITIVE LOGITS

 eleph

0.64

xual

0.62

quartered

0.61

selage

0.60

avorite

0.60

aterasu

0.59

MpServer

0.59

UCT

0.58

ukong

0.55

worms

0.55

Activations Density 1.361%

legal or regulatory terms and actions

terms related to eligibility, restrictions, and regulatory concepts

No Comments

No Known Activations