INDEX

Explanations

mentions of military units or organizations

oai_token-act-pair · gpt-3.5-turbo

references to the term "Corps"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

izer

-0.79

èª

-0.77

jad

-0.71

izers

-0.69

selves

-0.66

*/(

-0.64

 Palin

-0.63

iser

-0.63

âĹ¼

-0.63

ãĥĥãĤ¯

-0.62

POSITIVE LOGITS

naire

1.22

 Corps

0.91

hire

0.88

ombat

0.88

xon

0.86

naires

0.82

eteria

0.82

esan

0.82

 Headquarters

0.82

hip

0.81

Activations Density 0.015%

mentions of military units or organizations

references to the term "Corps"

No Comments

No Known Activations