INDEX

Explanations

words related to the act of publishing

oai_token-act-pair · gpt-3.5-turbo

instances of the word "publishing"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Antar

-0.77

igslist

-0.74

Ĭ±

-0.70

ascar

-0.69

andr

-0.67

llan

-0.67

olulu

-0.67

ichael

-0.66

ibur

-0.64

eric

-0.63

POSITIVE LOGITS

lisher

1.42

lishing

1.37

lishes

1.07

 RELE

0.88

 publishing

0.88

 publish

0.87

 publishes

0.87

 Kafka

0.85

rics

0.83

Pub

0.82

Activations Density 0.022%

words related to the act of publishing

instances of the word "publishing"

No Comments

No Known Activations