INDEX

Explanations

people's names, specifically "Kathleen"

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals, particularly those named Kathleen, and mentions of confidentiality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

opia

-0.90

runner

-0.87

nels

-0.85

ocom

-0.84

abe

-0.80

resses

-0.80

alter

-0.78

ologies

-0.77

urity

-0.75

alls

-0.74

POSITIVE LOGITS

illac

0.75

 Mechdragon

0.67

 Wynne

0.67

 chloride

0.64

 icing

0.63

 sworn

0.62

RAW

0.62

 ILCS

0.61

 Mamm

0.61

 Quarterly

0.60

Activations Density 0.088%

people's names, specifically "Kathleen"

references to specific individuals, particularly those named Kathleen, and mentions of confidentiality

No Comments

No Known Activations