INDEX

Explanations

ellipses within sentences

oai_token-act-pair · gpt-3.5-turbo

ellipses that indicate continuation or omission in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 attest

-0.75

 merit

-0.74

 outl

-0.73

 empath

-0.73

 indemn

-0.72

 purse

-0.72

 cradle

-0.72

 strength

-0.71

 wielded

-0.69

ividual

-0.68

POSITIVE LOGITS

BUT

1.07

 âĢİ

0.92

etc

0.89

yet

0.85

why

0.84

Bah

0.82

sort

0.82

they

0.80

 Appears

0.79

please

0.79

Activations Density 0.031%

ellipses within sentences

ellipses that indicate continuation or omission in text

No Comments

No Known Activations