INDEX

Explanations

names of places or people

oai_token-act-pair · gpt-3.5-turbo

repetitions of the letter 'd'

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 constitu

-0.79

OIL

-0.75

Nun

-0.75

éĹĺ

-0.72

 Remem

-0.71

EStream

-0.64

zai

-0.64

 Bris

-0.62

 reusable

-0.60

 suscept

-0.60

POSITIVE LOGITS

ynamic

1.38

iamond

1.23

ividual

1.22

ynam

1.16

etermin

1.15

orf

1.15

elta

1.15

etermined

1.15

iary

1.12

aniel

1.11

Activations Density 0.056%

names of places or people

repetitions of the letter 'd'

No Comments

No Known Activations