INDEX

Explanations

locations and cities

oai_token-act-pair · gpt-3.5-turbo

place names and geographical references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

lyak

-0.77

Ü

-0.75

VALUE

-0.73

onym

-0.67

Larry

-0.67

schild

-0.67

NASA

-0.66

 Surviv

-0.66

Mach

-0.65

ADRA

-0.64

POSITIVE LOGITS

shire

1.08

 Borough

0.99

 City

0.89

 Gardens

0.89

 Junction

0.87

 Palace

0.85

wich

0.85

 Heights

0.83

 Albion

0.83

 Rugby

0.83

Activations Density 0.104%

locations and cities

place names and geographical references

No Comments

No Known Activations