INDEX

Explanations

names of political figures

oai_token-act-pair · gpt-3.5-turbo

mentions of the Gandhi family and its dynamics

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ccording

-0.70

essee

-0.68

lations

-0.66

eric

-0.65

ologies

-0.65

LEASE

-0.64

 Webster

-0.63

ECTION

-0.63

ĨĴ

-0.62

ATTLE

-0.62

POSITIVE LOGITS

 Gandhi

1.21

 Jinn

0.93

 Sharma

0.80

artz

0.75

stones

0.73

weed

0.73

Neh

0.70

wu

0.69

 Sabha

0.68

 Guru

0.68

Activations Density 0.016%

names of political figures

mentions of the Gandhi family and its dynamics

No Comments

No Known Activations