INDEX

Explanations

references to or mentions of military ranks, specifically sergeants

oai_token-act-pair · gpt-3.5-turbo

references to military ranks, particularly "sergeant."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ahime

-0.78

issues

-0.76

uras

-0.73

phal

-0.72

bows

-0.71

apest

-0.71

asons

-0.70

ories

-0.70

Tea

-0.69

laus

-0.67

POSITIVE LOGITS

geant

1.28

 sergeant

1.14

 Sergeant

1.07

Sgt

0.98

 colonel

0.94

utenant

0.84

 lieutenant

0.77

 Corps

0.76

 officer

0.72

rible

0.71

Activations Density 0.013%

references to or mentions of military ranks, specifically sergeants

references to military ranks, particularly "sergeant."

No Comments

No Known Activations