INDEX

Explanations

phrases related to decision-making and personal preferences

oai_token-act-pair · gpt-3.5-turbo

references to personal beliefs and societal values

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ivas

-0.66

uilt

-0.64

ocard

-0.64

enegger

-0.63

eters

-0.63

adr

-0.62

claimer

-0.62

ilogy

-0.61

arij

-0.60

apego

-0.59

POSITIVE LOGITS

 boil

0.73

 outweigh

0.73

 besides

0.72

viz

0.72

 happening

0.70

âĢ¦"

0.69

.",

0.69

 undone

0.66

 happen

0.64

 sauce

0.63

Activations Density 0.647%

phrases related to decision-making and personal preferences

references to personal beliefs and societal values

No Comments

No Known Activations