INDEX

Explanations

the name "Sean" preceded by varying contexts and actions

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Sean" 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

internet

-0.78

racted

-0.68

changed

-0.65

icted

-0.65

 tender

-0.65

stract

-0.64

 subp

-0.63

yrinth

-0.63

inarily

-0.62

untarily

-0.62

POSITIVE LOGITS

 Hannity

1.29

 Spicer

1.10

Sean

0.86

 Gallup

0.82

 Payton

0.81

apon

0.79

 Parker

0.78

 Sullivan

0.78

 Trend

0.78

Lear

0.78

Activations Density 0.026%

the name "Sean" preceded by varying contexts and actions

mentions of the name "Sean" in various contexts

No Comments

No Known Activations