INDEX

Explanations

information related to show premieres, releases, and details

oai_token-act-pair · gpt-3.5-turbo

mentions of media availability and release details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ndra

-0.93

zsche

-0.78

vati

-0.77

conservancy

-0.75

rious

-0.75

 crem

-0.69

rous

-0.69

bek

-0.69

quo

-0.68

thy

-0.66

POSITIVE LOGITS

 theaters

1.21

DVD

1.13

 paperback

1.11

 Kindle

1.10

 ebook

1.09

 iTunes

1.01

DRM

1.01

 theat

1.00

DVD

1.00

 formats

0.99

Activations Density 0.848%

information related to show premieres, releases, and details

mentions of media availability and release details

No Comments

No Known Activations