INDEX

Explanations

mentions of military or authoritative figures, specifically commanders

oai_token-act-pair · gpt-3.5-turbo

references to military commanders

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

eat

-0.73

pher

-0.71

ether

-0.67

apers

-0.65

oric

-0.65

roma

-0.62

encers

-0.62

aver

-0.62

ramid

-0.61

apy

-0.61

POSITIVE LOGITS

 commander

0.93

 Commander

0.91

chief

0.90

 guiActiveUn

0.83

 colonel

0.81

ufact

0.79

 commanders

0.78

cknow

0.75

utenant

0.73

 officer

0.73

Activations Density 0.014%

mentions of military or authoritative figures, specifically commanders

references to military commanders

No Comments

No Known Activations