INDEX

Explanations

phrases related to war and military operations in cities

oai_token-act-pair · gpt-3.5-turbo

references to cities in conflict zones

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

Scot

-0.91

Lear

-0.91

wcsstore

-0.77

Reviewer

-0.77

Leary

-0.76

Recipe

-0.74

 Mercury

-0.74

ONEY

-0.72

 Richie

-0.69

Stud

-0.67

POSITIVE LOGITS

 Idlib

1.20

 Aleppo

1.10

 Raqqa

1.04

 Homs

1.03

 Mosul

0.99

 Donetsk

0.99

 outskirts

0.97

qqa

0.96

 Abbas

0.95

 mosques

0.94

Activations Density 0.210%

phrases related to war and military operations in cities

references to cities in conflict zones

No Comments

No Known Activations