INDEX

Explanations

phrases indicating a decision or consequence

oai_token-act-pair · gpt-3.5-turbo

conditional phrases indicating potential risks or consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

emouth

-0.78

OST

-0.72

owered

-0.71

ascus

-0.67

resents

-0.66

essential

-0.66

uded

-0.65

keyes

-0.64

IME

-0.63

uner

-0.63

POSITIVE LOGITS

 else

1.69

Else

1.20

 perish

1.18

 risk

1.11

 starve

1.05

 suffer

1.05

 alternatively

1.03

 forfeit

0.99

 worse

0.98

die

0.96

Activations Density 0.120%

phrases indicating a decision or consequence

conditional phrases indicating potential risks or consequences

No Comments

No Known Activations