INDEX

Explanations

the phrase "no wonder."

oai_token-act-pair · gpt-3.5-turbo

expressions of disbelief or surprise

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

jri

-0.73

ider

-0.68

aditional

-0.67

abase

-0.65

aith

-0.65

 ledger

-0.64

escription

-0.63

ictionary

-0.62

 experimented

-0.62

ature

-0.62

POSITIVE LOGITS

why

1.00

WHY

0.81

why

0.74

forth

0.70

ioned

0.66

McA

0.63

forward

0.63

stadt

0.63

!--

0.62

rand

0.61

Activations Density 0.034%

the phrase "no wonder."

expressions of disbelief or surprise

No Comments

No Known Activations