INDEX

Explanations

references to a specific entity named "Per"

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "Per" in various contexts

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

Not in Any Lists

No Comments

Negative Logits

INESS

-0.72

aiden

-0.69

DERR

-0.67

å¸

-0.67

 pneum

-0.65

ATIONAL

-0.65

 Lazarus

-0.63

MpServer

-0.61

naires

-0.61

 dwar

-0.59

POSITIVE LOGITS

cussion

1.30

uvian

1.29

malink

1.28

forming

1.25

mission

1.23

imeter

1.21

ipher

1.21

secution

1.20

pet

1.20

secut

1.19

Activations Density 0.014%

references to a specific entity named "Per"

mentions of the word "Per" in various contexts

No Comments

No Known Activations