INDEX

Explanations

domain-related terms or phrases

oai_token-act-pair · gpt-3.5-turbo

references to specific domain names and domain-related topics

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

 Clement

-0.82

tics

-0.81

tical

-0.67

eph

-0.66

pter

-0.65

thus

-0.65

 Fulton

-0.65

aquin

-0.64

hani

-0.63

hower

-0.62

POSITIVE LOGITS

 domain

0.82

 domains

0.81

 regist

0.80

domain

0.76

 controller

0.75

 registrations

0.75

plates

0.74

 controllers

0.74

Domain

0.72

 name

0.72

Activations Density 0.028%

domain-related terms or phrases

references to specific domain names and domain-related topics

No Comments

No Known Activations