INDEX

Explanations

proper nouns related to locations, specifically focusing on cities and towns

oai_token-act-pair · gpt-3.5-turbo

mentions of the city Sheffield

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

opsy

-0.77

naire

-0.73

ose

-0.70

 Genie

-0.70

oses

-0.69

osed

-0.68

egal

-0.68

ocr

-0.67

NCT

-0.65

uct

-0.63

POSITIVE LOGITS

 Sheffield

1.23

ffield

0.97

sburg

0.90

 Peaks

0.83

shire

0.75

 Slater

0.72

 Glas

0.72

bridge

0.69

borough

0.68

 Falls

0.68

Activations Density 0.004%

proper nouns related to locations, specifically focusing on cities and towns

mentions of the city Sheffield

No Comments

No Known Activations