INDEX

Explanations

terms related to military and conflict, particularly actions involving troops, prisoners, rebels, and volunteers

oai_token-act-pair · gpt-3.5-turbo

terms related to military and labor groups

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

cale

-1.24

aurus

-1.22

mith

-1.15

ources

-1.06

heet

-1.05

ervatives

-1.04

avers

-0.99

paces

-0.97

ynthesis

-0.97

orem

-0.96

POSITIVE LOGITS

 visitation

0.75

 Worker

0.74

holder

0.73

 pilot

0.71

 counts

0.69

 activity

0.69

 airliner

0.68

 corps

0.68

 visas

0.66

 motor

0.63

Activations Density 0.103%

terms related to military and conflict, particularly actions involving troops, prisoners, rebels, and volunteers

terms related to military and labor groups

No Comments

No Known Activations