INDEX

Explanations

proper names related to the name "Patrick"

oai_token-act-pair · gpt-3.5-turbo

the name "Patrick" 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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

TOR

-0.73

nexus

-0.73

ð

-0.72

ofi

-0.71

schild

-0.71

perse

-0.69

DIV

-0.69

scape

-0.68

enegger

-0.68

ells

-0.67

POSITIVE LOGITS

 Patrick

0.96

 Leah

0.87

 Pearce

0.83

 Reilly

0.82

 Patterson

0.81

Bat

0.80

 Murphy

0.79

 Duffy

0.79

 Byrne

0.78

 Stewart

0.77

Activations Density 0.013%

proper names related to the name "Patrick"

the name "Patrick" in various contexts

No Comments

No Known Activations