INDEX

Explanations

the word "why"

oai_token-act-pair · gpt-3.5-turbo

the phrase "that's why" indicating reasons or justifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ty

-0.65

rav

-0.64

 annihil

-0.63

MM

-0.62

kil

-0.61

 yard

-0.60

 transm

-0.60

rop

-0.59

 nucleus

-0.58

room

-0.58

POSITIVE LOGITS

why

0.94

soever

0.89

 Canaver

0.81

forth

0.70

ratulations

0.68

forward

0.68

ioned

0.66

why

0.66

WHY

0.66

terday

0.66

Activations Density 0.036%

the word "why"

the phrase "that's why" indicating reasons or justifications

No Comments

No Known Activations