INDEX

Explanations

words related to viewing or accessing content such as "View"

oai_token-act-pair · gpt-3.5-turbo

references to the word "View" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

TPS

-0.75

gob

-0.75

terday

-0.69

 exhausted

-0.63

 quotas

-0.63

 seas

-0.61

 sack

-0.61

 summons

-0.61

 piping

-0.61

 pump

-0.60

POSITIVE LOGITS

 View

3.99

view

2.32

 VIEW

2.26

View

2.24

 view

2.05

 Views

1.92

 views

1.54

views

1.48

VIEW

1.47

 viewer

1.32

Activations Density 0.016%

words related to viewing or accessing content such as "View"

references to the word "View" and its variations

No Comments

No Known Activations