INDEX

Explanations

the name "Phil" mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Phil."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CLASSIFIED

-0.78

 suffix

-0.63

Demand

-0.62

 unauthorized

-0.62

 Unlimited

-0.62

 pace

-0.62

TAM

-0.61

 containment

-0.60

 unfavorable

-0.59

 enrol

-0.59

POSITIVE LOGITS

anthrop

1.54

istine

1.32

harm

1.28

adel

1.15

adelphia

1.12

ando

1.09

andering

1.08

oton

1.01

orio

1.01

omon

0.97

Activations Density 0.018%

the name "Phil" mentioned in the text

mentions of the name "Phil."

No Comments

No Known Activations