INDEX

Explanations

information related to updates, cooperation, commitments, and support

oai_token-act-pair · gpt-3.5-turbo

phrases indicating commitment to transparency and accountability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Untitled

-0.79

soDeliveryDate

-0.67

?),

-0.66

opter

-0.65

?).

-0.63

 forgot

-0.63

 dunno

-0.62

guy

-0.62

perture

-0.62

irement

-0.61

POSITIVE LOGITS

 ourselves

1.05

 vigorously

0.97

 vigilant

0.90

 robust

0.85

 vigil

0.83

 vigorous

0.81

 diligent

0.81

 strive

0.79

our

0.78

 principled

0.78

Activations Density 0.529%

information related to updates, cooperation, commitments, and support

phrases indicating commitment to transparency and accountability

No Comments

No Known Activations