INDEX

Explanations

phrases related to giving something away

oai_token-act-pair · gpt-3.5-turbo

phrases related to giving away or donating items

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

IFrame

Link

Negative Logits

sis

-0.74

 Presbyter

-0.70

 Hispan

-0.69

anches

-0.69

xual

-0.68

iard

-0.68

ensen

-0.67

itia

-0.66

 Strauss

-0.66

zo

-0.66

POSITIVE LOGITS

Redd

0.70

 giveaway

0.69

 immortality

0.69

doors

0.69

 Donation

0.67

 goodbye

0.67

urst

0.65

ebook

0.62

 charity

0.62

android

0.62

Activations Density 0.021%

phrases related to giving something away

phrases related to giving away or donating items

No Known Activations