INDEX

Explanations

individual clauses that are part of a list

oai_token-act-pair · gpt-3.5-turbo

statements pertaining to warnings or alerts about potential dangers or risks

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

rha

-0.53

abama

-0.52

Pac

-0.52

cipled

-0.51

pac

-0.50

 steadfast

-0.47

 toget

-0.47

cy

-0.47

 discipline

-0.46

gal

-0.46

POSITIVE LOGITS

igslist

0.57

eday

0.56

Write

0.55

soDeliveryDate

0.55

hovah

0.54

oother

0.54

"\

0.54

zhen

0.53

wered

0.53

Downloadha

0.53

Activations Density 2.277%

individual clauses that are part of a list

statements pertaining to warnings or alerts about potential dangers or risks

No Comments

No Known Activations