INDEX

Explanations

social media platform-related terms and statistics

oai_token-act-pair · gpt-3.5-turbo

references to social media platforms and their interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Greenberg

-0.72

zik

-0.68

abal

-0.67

haus

-0.66

bach

-0.65

etts

-0.65

cephal

-0.63

ivas

-0.63

nil

-0.62

hawks

-0.60

POSITIVE LOGITS

 Mehran

0.87

LinkedIn

0.74

 Whats

0.72

 subscribing

0.70

 subscribe

0.70

Subscribe

0.66

iframe

0.66

 Tumblr

0.66

docker

0.65

outube

0.63

Activations Density 0.047%

social media platform-related terms and statistics

references to social media platforms and their interactions

No Comments

No Known Activations