INDEX

Explanations

references to programming languages and coding commands

oai_token-act-pair · gpt-3.5-turbo

phrases indicating plans or intentions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

estate

-0.76

 Reincarnated

-0.74

rament

-0.73

bred

-0.72

$$$$

-0.71

icide

-0.70

 mortal

-0.69

ibu

-0.68

 roadside

-0.68

bush

-0.67

POSITIVE LOGITS

 informative

1.08

 Cosponsors

0.96

 Topics

0.96

 topics

0.95

 summarize

0.94

isode

0.90

 overarching

0.89

utorial

0.85

Meta

0.85

 overview

0.83

Activations Density 0.937%

references to programming languages and coding commands

phrases indicating plans or intentions

No Comments

No Known Activations