INDEX

Explanations

locations or military bases with the word "Fort" in their names

oai_token-act-pair · gpt-3.5-turbo

references to different military forts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

lihood

-0.61

henko

-0.61

Companies

-0.60

senal

-0.60

gger

-0.60

pert

-0.58

Accessory

-0.57

 polarized

-0.56

 Primordial

-0.55

 chromosomes

-0.55

POSITIVE LOGITS

 Lauderdale

1.27

uitous

1.27

itude

1.22

ieth

1.15

resses

1.00

 Worth

1.00

dinand

0.97

itud

0.96

itudes

0.90

anamo

0.88

Activations Density 0.024%

locations or military bases with the word "Fort" in their names

references to different military forts

No Known Activations