INDEX

Explanations

references to the term "Te" in a variety of contexts

oai_token-act-pair · gpt-3.5-turbo

the occurrences of the term "Te" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ãģį

-0.70

ãĥ¼ãĥĨ

-0.70

 Hawks

-0.69

ItemTracker

-0.68

ividual

-0.68

etheless

-0.67

iasis

-0.66

 footing

-0.66

espie

-0.65

éĹĺ

-0.64

POSITIVE LOGITS

achable

1.32

acher

1.13

aching

1.13

achers

1.08

lem

1.06

levision

1.06

arers

1.03

brate

1.03

lev

1.01

legram

1.01

Activations Density 0.013%

references to the term "Te" in a variety of contexts

the occurrences of the term "Te" in various contexts

No Comments

No Known Activations