INDEX

Explanations

phrases related to leaving or not leaving something

oai_token-act-pair · gpt-3.5-turbo

phrases that convey absence or leaving something behind

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

ML

-0.82

 Cosponsors

-0.81

GW

-0.72

NESS

-0.67

Stats

-0.64

GW

-0.64

adj

-0.63

rix

-0.62

ML

-0.62

MN

-0.62

POSITIVE LOGITS

 intact

1.10

 untouched

1.09

 unanswered

1.06

 undone

1.02

 unsatisf

0.97

 unfinished

0.95

 footprints

0.94

 unatt

0.92

 unexpl

0.90

 residue

0.89

Activations Density 0.185%

phrases related to leaving or not leaving something

phrases that convey absence or leaving something behind

No Comments

No Known Activations