INDEX

Explanations

specific last names

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Carr" or terms related to it

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

ĨĴ

-0.86

ku

-0.77

 Pixie

-0.74

lasses

-0.68

utral

-0.67

£ı

-0.66

dayName

-0.66

¥µ

-0.64

xual

-0.62

zza

-0.61

POSITIVE LOGITS

agher

1.06

abilia

0.91

agh

0.91

anging

0.89

anged

0.89

issa

0.89

INGTON

0.89

andom

0.87

ange

0.85

abeth

0.85

Activations Density 0.015%

specific last names

mentions of the name "Carr" or terms related to it

No Comments

No Known Activations