INDEX

Explanations

mentions of the name "Sean" at a significant degree of activation

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Sean"

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

 subp

-0.84

yrinth

-0.79

 tender

-0.78

hov

-0.77

 circ

-0.72

drm

-0.72

pired

-0.70

 redeem

-0.66

-0.65

 situated

-0.64

POSITIVE LOGITS

Sean

1.22

 Hannity

1.12

 Spicer

0.97

 Sean

0.91

 Payton

0.87

apon

0.87

 Patrick

0.85

ason

0.83

 Hayes

0.83

eman

0.79

Activations Density 0.008%

mentions of the name "Sean" at a significant degree of activation

occurrences of the name "Sean"

No Comments

No Known Activations