INDEX

Explanations

strings of words containing technical terms and recommendations

oai_token-act-pair · gpt-3.5-turbo

content related to explanations and fundamental concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 afterwards

-0.68

=]

-0.68

 versa

-0.62

 accordingly

-0.60

 theirs

-0.60

 thereto

-0.59

 alas

-0.59

 afterward

-0.58

 latter

-0.58

 likewise

-0.57

POSITIVE LOGITS

 IPCC

0.79

 Canaver

0.73

osate

0.72

 ASIC

0.69

NBN

0.69

Bitcoin

0.67

oplan

0.67

bitcoin

0.66

 Bitcoin

0.66

 comet

0.66

Activations Density 1.952%

strings of words containing technical terms and recommendations

content related to explanations and fundamental concepts

No Comments

No Known Activations