INDEX

Explanations

words related to signaling intentions or actions

oai_token-act-pair · gpt-3.5-turbo

terms related to signaling or indications of intent

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

sm

-0.81

enne

-0.77

iler

-0.71

page

-0.71

iling

-0.71

eenth

-0.69

ath

-0.69

 Chatt

-0.68

eatured

-0.67

 Torn

-0.66

POSITIVE LOGITS

 signaling

1.06

 signals

1.05

 signalling

0.96

 signs

0.95

 signaled

0.94

 signal

0.86

 Signs

0.85

 indications

0.85

 indicating

0.84

 sign

0.76

Activations Density 0.013%

words related to signaling intentions or actions

terms related to signaling or indications of intent

No Comments

No Known Activations