INDEX

Explanations

military ranks and titles

oai_token-act-pair · gpt-3.5-turbo

references to military ranks or titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

BOOK

-0.86

stakes

-0.76

icles

-0.75

zsche

-0.72

ebook

-0.69

heet

-0.69

sight

-0.66

ograp

-0.65

milo

-0.62

fulness

-0.62

POSITIVE LOGITS

 colonel

1.32

 Colonel

1.20

utenant

1.15

 Commander

1.09

 Governor

1.00

 commander

0.89

 General

0.86

 Command

0.84

 Superintendent

0.84

Capt

0.83

Activations Density 0.041%

military ranks and titles

references to military ranks or titles

No Comments

No Known Activations