INDEX

Explanations

specific mentions of the name "Edward"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Edward."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

nda

-0.71

place

-0.68

 snail

-0.63

 sensit

-0.62

assian

-0.62

tsky

-0.62

empl

-0.61

kick

-0.60

 internationally

-0.59

calling

-0.59

POSITIVE LOGITS

 Edward

1.07

 Snowden

1.04

 Byrne

0.86

sson

0.85

ilant

0.85

Edward

0.83

 Cullen

0.76

 Nero

0.75

rey

0.75

 Heath

0.74

Activations Density 0.004%

specific mentions of the name "Edward"

mentions of the name "Edward."

No Comments

No Known Activations